{"id":127,"date":"2014-08-30T20:24:49","date_gmt":"2014-08-30T20:24:49","guid":{"rendered":"http:\/\/localhost\/testwebsite\/?page_id=127"},"modified":"2025-11-05T16:30:49","modified_gmt":"2025-11-05T16:30:49","slug":"publications","status":"publish","type":"page","link":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"<p><em><span style=\"color: #ff0000;\"><b>Note, we add all peer reviewed articles to this\u00a0list, and sometimes\u00a0also arXiv papers (but not all arXiv papers).<\/b><\/span><\/em><\/p>\n<p><strong>Books<\/strong><\/p>\n<ul>\n<li>B. Savchynskyy <a href=\"https:\/\/www.nowpublishers.com\/article\/Details\/CGV-084\">Discrete Graphical Models &#8211; An Optimization Perspective<\/a> Text-book. <em> Now Publishers, Special Issue on Foundations and Trends in Computer Graphics and Vision, 2019<\/em>. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/book-graphical-models-plain-version.pdf\">pdf with a tech. report formatting<\/a>]<\/li>\n<li>&#8220;<a href=\"https:\/\/mitpress.mit.edu\/books\/markov-random-fields-vision-and-image-processing\">Markov Random Fields for Vision and Image Processing<\/a>&#8220;, Edited by Andrew Blake, Pushmeet Kohli and Carsten Rother, MIT press 2011.<\/li>\n<\/ul>\n<p><strong>2025<\/strong><\/p>\n<ul>\n<li>Tomas Dlask, Bogdan Savchynskyy<br \/>\n\u201cRelative-Interior Solution for (Incomplete) Linear Assignment Problem with Applications to Quadratic Assignment Problem\u201d<br \/>\nAccepted to\u00a0<em>Annals of Mathematics and Artificial Intelligence<\/em>\u00a0[<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2301.11201\">preliminary version<\/a>]<\/li>\n<li>Max Kahl, Sebastian Stricker, Lisa Hutschenreiter, Florian Bernard, Carsten Rother, Bogdan Savchynskyy<br \/>\n\u201cTowards Optimizing Large-Scale Multi-Graph Matching in Bioimaging\u201d<br \/>\nAccepted to<em>\u00a0CVPR 2025<\/em>\u00a0[<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2406.18215\">Extended version<\/a>] [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/github.com\/vislearn\/multi-matching-optimization\">code<\/a>]<\/li>\n<li>M. Schuessler, L. Hormann, L., R. Dachselt, Blake, A., Rother, C. Gazing Heads: Investigating Gaze Perception in Video-Mediated Communication.\u00a0<span class=\"pub-meta-journal\">In\u00a0<em>ACM Transactions on Computer-Human Interaction (TOCHI)<\/em>\u00a0(Volume 31, Issue 3).\u00a0<\/span><span class=\"pub-meta-publisher\">Association for Computing Machinery,<\/span><span class=\"pub-meta-date\">2024.<\/span><span class=\"pub-meta-doi\"><a class=\"label label-info\" title=\"Go to: https:\/\/doi.org\/10.1145\/3660343\" href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/doi.org\/10.1145\/3660343\">10.1145\/3660343<\/a>.\u00a0<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/imld.de\/en\/research\/research-projects\/gazing-heads\/\">Project page<\/a><\/span><\/li>\n<li>D. Galperin, U. K\u00f6the (2025). \u201cAnalyzing Generative Models by Manifold Entropic Metrics\u201d,\u00a0<em>AISTATS 2025<\/em>, arXiv:2410.19426. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2410.19426\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2410.19426\">pdf<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/virtual.aistats.org\/virtual\/2025\/poster\/9646\">link<\/a>]<\/li>\n<li>S. Wahl, A. Rousselot, F. Draxler, U. K\u00f6the (2025). \u201cTRADE: Transfer of Distributions between External Conditions with Normalizing Flows\u201d,\u00a0<em>AISTATS 2025<\/em>, arXiv:2410.19492. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2410.19492\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2410.19492\">pdf<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/virtual.aistats.org\/virtual\/2025\/poster\/9449\">link<\/a>]<\/li>\n<li>P. Sorrenson, L. L\u00fchrs, H. Olischl\u00e4ger, U. K\u00f6the (2025): \u201cBeyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flows\u201d, arXiv:2506.01522. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2506.01522\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2506.01522\">pdf<\/a>]<\/li>\n<li>T. Adler, J.H. N\u00f6lke, A. Reinke, M. Tizabi, S. Gruber, D. Trofimova, L. Ardizzone, P. Jaeger, F. Buettner, U. K\u00f6the, L. Maier-Hein (2025). \u201cApplication-driven validation of posteriors in inverse problems\u201d,\u00a0<em>Medical Image Analysis,\u00a0<span class=\"anchor-text-container\"><span class=\"anchor-text\">Volume 101<\/span><\/span>, 103474<\/em>. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/doi.org\/10.1016\/j.media.2025.103474\">link<\/a>]<\/li>\n<\/ul>\n<p><strong>2024<\/strong><\/p>\n<ul>\n<li>D. Zavadski, D. Kal\u0161an, C. Rother. \u201cPrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage\u201d. accepted at ACCV 2024, arxiv:2409.09144 [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/www.arxiv.org\/abs\/2409.09144\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/www.arxiv.org\/pdf\/2409.09144\">pdf<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/github.com\/vislearn\/PrimeDepth\">code<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/vislearn.github.io\/PrimeDepth\/\">project<\/a>]<\/li>\n<li>P. Sorrenson, F. Draxler, A. Rousselot, S. Hummerich, U. K\u00f6the (2024). \u201cLearning Distributions on Manifolds with Free-Form Flows\u201d.\u00a0<em>NeurIPS 2024<\/em>, arXiv:2312.09852. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2312.09852\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2312.09852\">pdf<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/nips.cc\/virtual\/2024\/poster\/95225\">link<\/a>]<\/li>\n<li>M. Schmitt, V. Pratz, U. K\u00f6the, P. B\u00fcrkner, S. Radev (2024). \u201cConsistency Models for Scalable and Fast Simulation-Based Inference\u201d,\u00a0<em>NeurIPS 2024<\/em>, arXiv:2312.05440. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2312.05440\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2312.05440\">pdf<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/nips.cc\/virtual\/2024\/poster\/95775\">link<\/a>]<\/li>\n<li>D. Zavadski, J.-F. Feiden, C. Rother. \u201cControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems\u201d. ECCV 2024 Oral, [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2312.06573\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2312.06573\">pdf<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/github.com\/vislearn\/ControlNet-XS\">code<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/vislearn.github.io\/ControlNet-XS\/\">project<\/a>]<\/li>\n<li>T. Hodan, M. Sundermeyer, Y. Labb\u00e9, V. N. Nguyen, G. Wang, E. Brachmann, B. Drost, V. Lepetit, C. Rother, J. Matas. \u201cBOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects\u201d.\u00a0<em>Workshop on Computer Vision for Mixed Reality at CVPR 2024.<\/em>\u00a0[<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2403.09799\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2403.09799\">pdf<\/a>]<\/li>\n<li>F. Draxler, S. Wahl, C. Schn\u00f6rr, U. K\u00f6the (2024). \u201cOn the Universality of Volume-Preserving and Coupling-Based Normalizing Flows\u201d.\u00a0<i>ICML 2024<\/i>, arXiv:2402.06578. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/proceedings.mlr.press\/v235\/draxler24a.html\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2402.06578\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2402.06578\">pdf<\/a>]<\/li>\n<li>M. Schmitt, D. Ivanova, D. Habermann, P. B\u00fcrkner, U. K\u00f6the, S. Radev (2024). \u201cLeveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference\u201d,\u00a0<em>ICML 2024<\/em>,\u00a0arXiv:2310.04395. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/proceedings.mlr.press\/v235\/schmitt24a.html\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2310.04395\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2310.04395\">pdf<\/a>]<\/li>\n<li>F. Draxler, P. Sorrenson, A. Rousselot, L. Zimmerman, U. K\u00f6the (2024). \u201cFree-form flows: Make Any Architecture a Normalizing Flow\u201d.\u00a0<em>AISTATS 2024,\u00a0<\/em>arXiv:2310.16624<em>.<\/em>\u00a0[<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/proceedings.mlr.press\/v238\/draxler24a.html\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2310.16624\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2310.16624\">pdf<\/a>]<\/li>\n<li>P. Sorrenson, F. Draxler, A. Rousselot, S. Hummerich, L. Zimmerman, U. K\u00f6the (2024). \u201cLifting Architectural Constraints of Injective Flows\u201d.\u00a0<em>ICLR 2024<\/em>, arXiv:2306.01843. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/openreview.net\/forum?id=kBNIx4Biq4\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2306.01843\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2306.01843\">pdf<\/a>]<\/li>\n<li>D.H. Lehmann, B. Gomes, N. Vetter, O. Braun, A. Amr, T. Hilbel, J, M\u00fcller, U. K\u00f6the, C. Reich, E. Kayvanpour, F. Sedaghat-Hamedani, M. Meder, J. Haas, E. Ashley, W. Rottbauer, D. Felbel, R. Bekeredjian, H. Mahrholdt, A. Keller, P. Ong, A. Seitz, H. Hund, N. Geis, F. Andr\u00e9, S. Engelhardt, H.A. Katus, N. Frey, V. Heuveline, B. Meder (2024). \u201cPrediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modeling study of hospital data\u201d,\u00a0<em>The Lancet Digital Health<\/em>, 6(6):e407-e417<span class=\"meta-panel__middle\"><span class=\"meta-panel__pages\">. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/www.thelancet.com\/journals\/landig\/article\/PIIS2589-7500(24)00063-3\/fulltext\">link<\/a>]<\/span><\/span><\/li>\n<li>L. Elsem\u00fcller, H. Olischl\u00e4ger, M. Schmitt, P. B\u00fcrkner, U. K\u00f6the, S. Radev (2024). \u201cSensitivity-aware amortized Bayesian inference\u201d,\u00a0<em>Transactions on Machine Learning Research<\/em>,\u00a0arXiv:2310.11122. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/openreview.net\/forum?id=Kxtpa9rvM0\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2310.11122\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2310.11122\">pdf<\/a>]<\/li>\n<li>Siddharth Tourani, Carsten Rother, Muhammad Haris Khan, Bogdan Savchynskyy \u201cUnsupervised Deep Graph Matching Based on Cycle Consistency\u201d.\u00a0<em>AAAI 2024\u00a0<\/em>[<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2307.08930\">extended version<\/a>]<\/li>\n<li>M. Sch\u00fcssler, L. Hormann, R. Dachselt, A. Blake, C. Rother (2024). \u201cGazing Heads: Investigating Gaze Perception in Video-Mediated Communication\u201d.\u00a0<em>ACM Transactions on Computer-Human Interaction<\/em>. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/dl.acm.org\/doi\/10.1145\/3660343\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3660343\">pdf<\/a>]<\/li>\n<li>P. Lorenz, M. Fernandez, J. M\u00fcller, U. K\u00f6the (2024). \u201cDeciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors\u201d,\u00a0<em>ICML 2024 Next Generation of AI Safety Workshop<\/em>, arXiv:2406.15104. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/openreview.net\/forum?id=Lhmlvh7VTi\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2406.15104\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2406.15104\">pdf<\/a>]<\/li>\n<li>P. Sorrenson, D. Behrend-Uriarte, C. Schn\u00f6rr, U. K\u00f6the (2024). \u201cLearning Distances from Data with Normalizing Flows and Score Matching\u201d. arXiv:2407.09297. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2407.09297\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2407.09297\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2023<\/strong><\/p>\n<ul>\n<li>U. K\u00f6the, C. Rother (2023), eds.: \u201cPattern Recognition\u201d, Proceedings of 45th DAGM German Conference, DAGM GCPR 2023. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/link.springer.com\/book\/10.1007\/978-3-031-54605-1\">link<\/a>]<\/li>\n<li>F. Draxler, L. K\u00fchmichel, A. Rousselot, J. M\u00fcller, C. Schn\u00f6rr, U. K\u00f6the (2023). \u201cOn the Convergence Rate of Gaussianization with Random Rotations\u201d,\u00a0<em>ICML 2023<\/em>, arXiv:2306.13520. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/proceedings.mlr.press\/v202\/draxler23a.html\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2306.13520\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/pdf\/2306.13520\">pdf<\/a>]<\/li>\n<li>R. Schmier, U. K\u00f6the, C.N. Straehle (2023). \u201cPositive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data\u201d,\u00a0<em>Transactions on Machine Learning Research<\/em>, arXiv:2208.14024. [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/openreview.net\/forum?id=B4J40x7NjA\">link<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/arxiv.org\/abs\/2208.14024\">arxiv<\/a>], [<a href=\"https:\/\/web.archive.org\/web\/20250804162505\/https:\/\/openreview.net\/pdf?id=B4J40x7NjA\">pdf<\/a>]<\/li>\n<li>M. Sundermeyer, T. Hoda\u0148, Y. Labb\u00e9, G. Wang, E. Brachmann, B. Drost, C. Rother, J. Matas (2023). &#8220;BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects&#8221;. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2023\/03\/BOP_Challenge_2022.pdf\">pdf<\/a>]<\/li>\n<li>D.E. Kang, R. Klessen, V. Ksoll, L. Ardizzone, U. K\u00f6the, S. Glover (2023). &#8220;Noise-Net: Determining physical properties of HII regions reflecting observational uncertainties&#8221;, <em>Monthly Notices of the Royal Astronomical Society<\/em> (vol. 520, no. 4, pp. 4981-5001), arXiv:2301.03014. [<a href=\"https:\/\/academic.oup.com\/mnras\/article\/520\/4\/4981\/6982917\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2301.03014\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2301.03014\">pdf<\/a>]<\/li>\n<li>T. Bister, M. Erdmann, U. K\u00f6the, J. Schulte (2023). &#8220;Inference of astrophysical parameters with a conditional invertible neural network&#8221;,\u00a0 Journal of Physics: Conference Series (Vol. 2438, No. 1, p. 012094). [<a href=\"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2438\/1\/012094\/meta\">link<\/a>], [<a href=\"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2438\/1\/012094\/pdf\">pdf<\/a>]<\/li>\n<li>Tomas Dlask, Bogdan Savchynskyy (2023). &#8220;Relative-Interior Solution for (Incomplete) Linear Assignment Problem with Applications to Quadratic Assignment Problem&#8221; [<a href=\"https:\/\/arxiv.org\/pdf\/2301.11201\">arxiv<\/a>]<\/li>\n<li>J. Wider, J. Kruse, N. Weitzel, J. B\u00fchler, U. K\u00f6the, K. Rehfeld (2023). &#8220;Towards Learned Emulation of Interannual Water Isotopologue Variations in General Circulation Models&#8221;, arXiv:2301.13462. [<a href=\"https:\/\/arxiv.org\/abs\/2301.13462\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2301.13462\">pdf<\/a>]<\/li>\n<li>S. Radev, M. Schmitt, V. Pratz, U. Picchini, U. K\u00f6the, P.-C. B\u00fcrkner (2023). &#8220;JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models&#8221;, arXiv:2302.09125. [<a href=\"https:\/\/arxiv.org\/abs\/2302.09125\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2302.09125\">pdf<\/a>]<\/li>\n<li>J. M\u00fcller, S. Radev, R. Schmier, F. Draxler, C. Rother, U. K\u00f6the (2023). &#8220;Finding Competence Regions in Domain Generalization&#8221;, arXiv:2303.09989. [<a href=\"https:\/\/arxiv.org\/abs\/2303.09989\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2303.09989\">pdf<\/a>]<\/li>\n<li>K. Dreher, L. Ayala, M. Schellenberg, M. H\u00fcbner, J.-H. N\u00f6lke, T. Adler, S. Seidlitz, J. Sellner, A. Studier-Fischer, J. Gr\u00f6hl, F. Nickel, U. K\u00f6the, A. Seitel, L. Maier-Hein (2023). &#8220;Unsupervised Domain Transfer with Conditional Invertible Neural Networks&#8221;, arXiv:2303.10191. [<a href=\"https:\/\/arxiv.org\/abs\/2303.10191\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2303.10191\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2022<\/strong><\/p>\n<ul>\n<li>F. Draxler, C. Schn\u00f6rr, U. K\u00f6the (2022). &#8220;Whitening Convergence Rate of Coupling-Based Normalizing Flows&#8221;, NeurIPS 2022 (oral presentation), <span class=\"arxivid\">arXiv:2210.14032.<\/span> [<a href=\"https:\/\/arxiv.org\/abs\/2210.14032\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2210.14032\">pdf<\/a>]<\/li>\n<li>S. Haller, L. Feineis, L. Hutschenreiter, F. Bernard, C. Rother, D. Kainm\u00fcller, P. Swoboda, B. Savchynskyy (2022). &#8220;A Comparative Study of Graph Matching Algorithms in Computer Vision&#8221;, ECCV 2022. [<a href=\"https:\/\/arxiv.org\/abs\/2207.00291\">arxiv<\/a>] [<a href=\"https:\/\/arxiv.org\/pdf\/2207.00291.pdf\">pdf<\/a>] [<a href=\"https:\/\/vislearn.github.io\/gmbench\/\">website<\/a>]<\/li>\n<li>T. Leistner, R. Mackowiak, L. Ardizzone, U. K\u00f6the, C. Rother (2022). &#8220;Towards Multimodal Depth Estimation from Light Fields&#8221;, CVPR 2022, arXiv:2203.16542. [<a href=\"https:\/\/openaccess.thecvf.com\/content\/CVPR2022\/html\/Leistner_Towards_Multimodal_Depth_Estimation_From_Light_Fields_CVPR_2022_paper.html\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2203.16542\">arxiv<\/a>], [<a href=\"https:\/\/openaccess.thecvf.com\/content\/CVPR2022\/papers\/Leistner_Towards_Multimodal_Depth_Estimation_From_Light_Fields_CVPR_2022_paper.pdf\">pdf<\/a>]<\/li>\n<li>U. K\u00f6the (2022). &#8220;Mensch und Automat \u2013 Die Rolle von Zufall und Determinismus&#8221;, Forum Marsilius-Kolleg 22(2). [<a href=\"https:\/\/journals.ub.uni-heidelberg.de\/index.php\/forum-mk\/article\/view\/92716\">link<\/a>], [<a href=\"https:\/\/journals.ub.uni-heidelberg.de\/index.php\/forum-mk\/article\/view\/92716\/87782\">pdf<\/a>]<\/li>\n<li>A. Bischops, S. Radev, U. K\u00f6the, S. Chen, P. Geldsetzer, M. Sarker, T.T. Su, F.A. Mohamed, N. Darwish, N.A. Ahmad, Sidi Ahmed Ould Baba, T. B\u00e4rnighausen, S. Barteit (2022). &#8220;Data Resource Profile: The Global School-based Student Health Survey\u2014behavioural risk and protective factors among adolescents&#8221;, International Journal of Epidemiology, dyac208. [<a href=\"https:\/\/academic.oup.com\/ije\/advance-article\/doi\/10.1093\/ije\/dyac208\/6814404\">link<\/a>], [<a href=\"https:\/\/academic.oup.com\/ije\/advance-article-pdf\/doi\/10.1093\/ije\/dyac208\/46901561\/dyac208.pdf\">pdf<\/a>]<\/li>\n<li>J. Kruse, B. Ellerhoff, U. K\u00f6the, K. Rehfeld (2022). &#8220;Conditional normalizing flow for predicting the occurrence of rare extreme events on long time scales&#8221;, EGU General Assembly 2022. [<a href=\"https:\/\/meetingorganizer.copernicus.org\/EGU22\/EGU22-8656.html\">link<\/a>], [<a href=\"https:\/\/meetingorganizer.copernicus.org\/EGU22\/EGU22-8656.html?pdf\">pdf<\/a>]<\/li>\n<li>M. T\u00f6lle, U. K\u00f6the, F. Andr\u00e9, B. Meder, S. Engelhardt (2022). &#8220;Content-Aware Differential Privacy with Conditional Invertible Neural Networks&#8221;, International Workshop on Distributed, Collaborative, and Federated Learning, Springer LNCS 13573, arXiv:2207.14625. [<a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-18523-6_9\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2207.14625\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2207.14625\">pdf<\/a>]<\/li>\n<li>M. Schmitt, P. B\u00fcrkner, U. K\u00f6the, S. Radev (2022). &#8220;Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks&#8221;, arXiv:2112.08866. [<a href=\"https:\/\/arxiv.org\/abs\/2112.08866\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2112.08866\">pdf<\/a>]<\/li>\n<li>R. Schmier, U. K\u00f6the, C.N. Straehle (2022). &#8220;Anomaly Detection using Contrastive Normalizing Flows&#8221;, arXiv:2208.14024. [<a href=\"https:\/\/arxiv.org\/abs\/2208.14024\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2208.14024\">pdf<\/a>]<\/li>\n<li>\n<div class=\"gs_citr\" tabindex=\"0\">L. Schumacher, P. B\u00fcrkner, A. Voss, U. K\u00f6the, S. Radev (2022). &#8220;Neural Superstatistics: A Bayesian Method for Estimating Dynamic Models of Cognition&#8221;, arXiv:2211.13165. [<a href=\"https:\/\/arxiv.org\/abs\/2211.13165\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2211.13165\">pdf<\/a>]<\/div>\n<\/li>\n<li>J. Fragemann, L. Ardizzone, J. Egger, J. Kleesiek (2022). &#8220;Review of Disentanglement Approaches for Medical Applications &#8211; Towards Solving the Gordian Knot of Generative Models in Healthcare&#8221;, MICCAI WS Medical Applications with Disentanglements (MAD), arXiv:2203.11132, 2022. [<a href=\"https:\/\/arxiv.org\/abs\/2203.11132\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2203.11132\">pdf<\/a>]<\/li>\n<li>J. Haldemann, V. Ksoll, D. Walter, Y. Alibert, R. Klessen, W. Benz, U. K\u00f6the, L. Ardizzone, C. Rother (2022). &#8220;Exoplanet Characterization using Conditional Invertible Neural Networks&#8221;, arXiv:2202.00027. [<a href=\"https:\/\/arxiv.org\/abs\/2202.00027\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2202.00027\">pdf<\/a>]<\/li>\n<li>D.E. Kang, E. Pellegrini, L. Ardizzone, R. Klessen, U. K\u00f6the, S. Glover, V. Ksoll (2022). &#8220;Emission-line diagnostics of HII regions using conditional Invertible Neural Networks&#8221;, <em>Monthly Notices of the Royal Astronomical Society<\/em>, 512(1):617\u2013647. [<a href=\"https:\/\/doi.org\/10.1093\/mnras\/stac222\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2201.08765\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2201.08765\">pdf<\/a>]<\/li>\n<li>T. Bister, M. Erdmann, U. K\u00f6the, J. Schulte (2022). &#8220;Inference of cosmic-ray source properties by conditional invertible neural networks&#8221;, The European Physical Journal C 82 (2)<b>,<\/b>171. [<a href=\"https:\/\/doi.org\/10.1140\/epjc\/s10052-022-10138-x\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2110.09493\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2110.09493\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2021<\/strong><\/p>\n<ul>\n<li>A. Sauer, K. Chitta, J. M\u00fcller, A. Geiger (2021). &#8220;Projected GANs converge faster&#8221;, NeurIPS 2021, arXiv:2111.01007, [<a href=\"https:\/\/arxiv.org\/abs\/2111.01007\">arxiv<\/a>], [<a href=\"https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/9219adc5c42107c4911e249155320648-Paper.pdf\">pdf<\/a>]<\/li>\n<li>E. Brachmann, M. Humenberger, C. Rother, T. Sattle (2021). &#8220;On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation&#8221;, ICCV 2021 [<a href=\"https:\/\/arxiv.org\/pdf\/2109.00524.pdf\">pdf<\/a>]<\/li>\n<li>L.Hutschenreiter, S. Haller, L. Feineis, C. Rother, D. Kainmueller, B. Savchynskyy (2021). &#8220;Fusion Moves for Graph Matching&#8221;, ICCV 2021 (oral presentation) [<a href=\"https:\/\/arxiv.org\/pdf\/2101.12085.pdf\">pdf<\/a>], [<a href=\"https:\/\/vislearn.github.io\/libmpopt\/iccv2021\">project page<\/a>]<\/li>\n<li>R. Mackowiak, L. Ardizzone, U. K\u00f6the, C. Rother (2021). &#8220;Generative Classifiers as a Basis for Trustworthy Image Classification&#8221;, CVPR 2021 (oral presentation), arXiv:2007.15036 [<a href=\"https:\/\/arxiv.org\/abs\/2007.15036\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2007.15036\">pdf<\/a>]<\/li>\n<li>E. Brachmann, C. Rother (2021). &#8220;Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC&#8221;, IEEE Transactions on Pattern Analysis and Machine Intelligence 2021, arXiv:2002.12324. [<a href=\"https:\/\/arxiv.org\/abs\/2002.12324\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2002.12324\">pdf<\/a>]<\/li>\n<li>J. Kruse, G. Detommaso, U. K\u00f6the, R. Scheichl (2021). &#8220;HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inference&#8221;, AAAI 2021, arXiv:1905.10687. [<a href=\"https:\/\/arxiv.org\/abs\/1905.10687\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/1905.10687\">pdf<\/a>]<\/li>\n<li>S. Radev, M. D&#8217;Alessandro, U. Mertens, A. Voss, U. K\u00f6the, P. B\u00fcrkner (2021). &#8220;Amortized Bayesian model comparison with evidential deep learning&#8221;, IEEE Trans. Neural Networks and Learning Systems, arXiv:2004.10629. [<a href=\"https:\/\/ieeexplore.ieee.org\/document\/9612724\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2004.10629\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2004.10629\">pdf<\/a>]<\/li>\n<li>S. Radev, F. Graw, S. Chen, N. Mutters, V. Eichel, T. B\u00e4rnighausen, U. K\u00f6the (2021). &#8220;OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany&#8221;, PLOS Computational Biology, arXiv:2010.00300. [<a href=\"https:\/\/journals.plos.org\/ploscompbiol\/article?id=10.1371\/journal.pcbi.1009472\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2010.00300\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2010.00300\">pdf<\/a>]<\/li>\n<li>J. M\u00fcller, R. Schmier, L. Ardizzone, C. Rother, U. K\u00f6the (2021). &#8220;Learning Robust Models Using The Principle of Independent Causal Mechanisms&#8221;, GCPR 2021 [<a href=\"https:\/\/arxiv.org\/abs\/2010.07167\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2010.07167\">pdf<\/a>]<\/li>\n<li>H. Lee, R. Herzog, J. Rexilius, C. Rother (2021). &#8220;Spatiotemporal Outdoor Lighting Aggregation on Image Sequences&#8221;, GCPR 2021<\/li>\n<li>P. Noever-Castelos, L. Ardizzone, C. Balzani (2021). &#8220;Model updating of wind turbine blade cross sections with invertible neural networks&#8221;, Wind Energy, 2021 [<a href=\"https:\/\/onlinelibrary.wiley.com\/doi\/full\/10.1002\/we.2687\">link<\/a>], [<a href=\"https:\/\/onlinelibrary.wiley.com\/doi\/pdfdirect\/10.1002\/we.2687?download=true\">pdf<\/a>]<\/li>\n<li>J. Kleesiek, B. Kersjes, K. Ueltzhoeffer, J. M. Murray, C. Rother, U. K\u00f6the, H. Schlemmer (2021). &#8220;Discovering Digital Tumor Signatures &#8211; Using Latent Code Representations to Manipulate and Classify Liver Lesions&#8221;, Cancers 2021. [<a href=\"https:\/\/www.mdpi.com\/2072-6694\/13\/13\/3108\">link<\/a>], [<a href=\"https:\/\/www.mdpi.com\/2072-6694\/13\/13\/3108\/pdf\">pdf<\/a>]<\/li>\n<li>A. Neishabouri, N. Wahl, A. Mairani, U. K\u00f6the, M. Bangert (2021). &#8220;Long short-term memory networks for proton dose calculation in highly heterogeneous tissues&#8221;, Medical Physics 48(4):1893-1908, arXiv:2006.06085 [<a href=\"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full\/10.1002\/mp.14658\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2006.06085\">arxiv<\/a>], [<a href=\"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdfdirect\/10.1002\/mp.14658?download=true\">pdf<\/a>]<\/li>\n<li>V.F. Ksoll, D. Gouliermis, E. Sabbi, J.E. Ryon, M. Robberto, M. Gennaro, R. Klessen, U. K\u00f6the, &#8230; &amp; A.E. Dolphin (2021). &#8220;Measuring Young Stars in Space and Time. I. The Photometric Catalog and Extinction Properties of N44&#8221;, The Astronomical Journal, 161(6), 256, arXiv:2012.00521. [<a href=\"https:\/\/iopscience.iop.org\/article\/10.3847\/1538-3881\/abee8b\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2012.00521\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2012.00521\">pdf<\/a>]<\/li>\n<li>V.F. Ksoll, D. Gouliermis, E. Sabbi, J.E. Ryon, M. Robberto, M. Gennaro, R. Klessen, U. K\u00f6the, &#8230; &amp; A.E. Dolphin (2021). &#8220;Measuring Young Stars in Space and Time. II. The Pre-main-sequence Stellar Content of N44&#8221;. The Astronomical Journal, 161(6), 257, arXiv:2012.00524. [<a href=\"https:\/\/iopscience.iop.org\/article\/10.3847\/1538-3881\/abee8c\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2012.00524\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2012.00524\">pdf<\/a>]<\/li>\n<li>B. Dillon, T. Plehn, C. Sauer, P. Sorrenson (2021). &#8220;Better latent spaces for better autoencoders&#8221;, SciPost Phys. 11, 061. [<a href=\"https:\/\/www.scipost.org\/SciPostPhys.11.3.061\">link<\/a>], [<a href=\"https:\/\/www.scipost.org\/SciPostPhys.11.3.061\/pdf\">pdf<\/a>]<\/li>\n<li>S. Bieringer, A. Butter, T. Heimel, S. H\u00f6che, U. K\u00f6the, T. Plehn, S. Radev (2021). &#8220;Measuring QCD Splittings with Invertible Networks&#8221;, SciPost Phys. 10, 126. [<a href=\"https:\/\/scipost.org\/10.21468\/SciPostPhys.10.6.126\">link<\/a>], [<a href=\"https:\/\/scipost.org\/SciPostPhys.10.6.126\/pdf\">pdf<\/a>]<\/li>\n<li>J.H. N\u00f6lke, T. Adler, J. Gr\u00f6hl, L. Ardizzone, C. Rother, U. K\u00f6the, L. Maier-Hein (2021). &#8220;Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging&#8221;, BVM 2021, arXiv:2011.05110. [<a href=\"https:\/\/arxiv.org\/abs\/2011.05110\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2011.05110\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2020<\/strong><\/p>\n<ul>\n<li>D. Trofimova, T. Adler, L. Kausch, L. Ardizzone, K. Maier-Hein, U. K\u00f6the, C. Rother, and L. Maier-Hein (2020). &#8220;Representing Ambiguity in Registration Problems with Conditional Invertible Neural Networks&#8221;, NeurIPs Medical Imaging 2020 [<a href=\"https:\/\/arxiv.org\/abs\/2012.08195\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2012.08195\">pdf<\/a>]<\/li>\n<li>L. Ardizzone, R. Mackowiak, C. Rother, U. K\u00f6the (2020). &#8220;Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification&#8221;, NeurIPS 2020 (oral presentation), arXiv:2001.06448 [<a href=\"https:\/\/arxiv.org\/abs\/2001.06448\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2001.06448\">pdf<\/a>]<\/li>\n<li>S. Radev, U. Mertens, A. Voss, L. Ardizzone, U. K\u00f6the (2020). &#8220;BayesFlow: Learning complex stochastic models with invertible neural networks&#8221;, IEEE Trans. Neural Networks and Learning Systems, doi:10.1109\/TNNLS.2020.3042395, arXiv:2003.06281. [<a href=\"https:\/\/ieeexplore.ieee.org\/document\/9298920\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2003.06281\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2003.06281\">pdf<\/a>]<\/li>\n<li>V.F. Ksoll, L. Ardizzone, R. Klessen, U. K\u00f6the, E. Sabbi, M. Robberto, D. Gouliermis, C. Rother, P. Zeidler, M. Gennaro (2020) &#8220;Stellar parameter determination from photometry using invertible neural networks&#8221;, Monthly Notices of the Royal Astronomical Society, Volume 499, Issue 4, Pages 5447\u20135485. [<a href=\"https:\/\/academic.oup.com\/mnras\/advance-article\/doi\/10.1093\/mnras\/staa2931\/5950348?guestAccessKey=590fe0a1-9ecf-4063-9196-49d4073cd561\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2007.08391\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2007.08391\">pdf<\/a>]<\/li>\n<li>H. Abu Alhaija, S.K. Mustikovela, J. Thies, V. Jampani, M. Nie\u00dfner, A. Geiger, C. Rother (2020) &#8220;Intrinsic Autoencoders for Joint Deferred Neural Rendering and Intrinsic Image Decomposition&#8221;, 3DV 2020. [<a href=\"https:\/\/arxiv.org\/pdf\/2006.16011.pdf\">arxiv<\/a>]<\/li>\n<li>C. Kamann, C. Rother (2020) &#8220;Benchmarking the Robustness of Semantic Segmentation Models with Respect to Common Corruptions&#8221;, IJCV 2020. [<a href=\"https:\/\/link.springer.com\/article\/10.1007%2Fs11263-020-01383-2\">link<\/a>]<\/li>\n<li>T. Hoda\u0148, M. Sundermeyer, B. Drost, Y. Labb\u00e9, E. Brachmann, F. Michel, C. Rother, J. Matas (2020). &#8220;BOP Challenge 2020 on 6D Object Localization&#8221;, ECCVW 2020. [<a href=\"https:\/\/arxiv.org\/pdf\/2009.07378.pdf\">arxiv<\/a>]<\/li>\n<li>F. Draxler, J. Schwarz, C. Schn\u00f6rr, U. K\u00f6the (2020). &#8220;Characterizing the Role of a Single Affine Coupling Layer in Affine Normalizing Flows&#8221;, GCPR 2020 (best paper honorable mention). [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2020\/08\/draxler2020characterizing.pdf\">pdf<\/a>] [<a href=\"https:\/\/youtu.be\/rIxY94zPPi0?t=134\">video<\/a>]<\/li>\n<li>J. Schwarz, F. Draxler, U. K\u00f6the, C. Schn\u00f6rr (2020). &#8220;Riemannian SOS-Polynomial Normalizing Flows&#8221;, GCPR 2020. [<a href=\"https:\/\/ipa.iwr.uni-heidelberg.de\/dokuwiki\/Papers\/Schwarz2020aa.pdf\">pdf<\/a>]<\/li>\n<li>L. Ardizzone, J. Kruse, C. L\u00fcth, N. Bracher, C. Rother, U. K\u00f6the (2020). &#8220;Conditional Invertible Neural Networks for Diverse Image-to-Image Translation&#8221;, GCPR 2020, arXiv:2105.02104. [<a href=\"https:\/\/www.springerprofessional.de\/conditional-invertible-neural-networks-for-diverse-image-to-imag\/18972490\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2105.02104\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2105.02104\">pdf<\/a>]<\/li>\n<li>C. Kamann, C. Rother (2020). &#8220;Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers&#8221;, ECCV 2020. <a href=\"https:\/\/www.ecva.net\/papers\/eccv_2020\/papers_ECCV\/papers\/123550375.pdf\">[link]<\/a><\/li>\n<li>H. Schilling, M. Gutsche, A. Brock, D. Sp\u00e4th, C. Rother, K. Krispin (2020). &#8220;Mind the Gap &#8211; A Benchmark for Dense Depth Prediction beyond Lidar&#8221;,\u00a02nd Workshop on Safe Artificial Intelligence for Automated Driving, in conjunction with CVPR 2020.<\/li>\n<li>P. Sorrenson, C. Rother, U. K\u00f6the (2020). &#8220;Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)&#8221;, Intl. Conf. Learning Representations (ICLR) [<a href=\"https:\/\/arxiv.org\/abs\/2001.04872\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2001.04872\">pdf<\/a>]<\/li>\n<li>M. Bellagente, A. Butter, G. Kasieczka, T. Plehn, A. Rousselot, R. Winterhalder, L. Ardizzone, U. K\u00f6the (2020). &#8220;Invertible networks or partons to detector and back again&#8221;, SciPost Phys. 9, 074 [<a href=\"https:\/\/scipost.org\/SciPostPhys.9.5.074\">link<\/a>], [<a href=\"https:\/\/scipost.org\/SciPostPhys.9.5.074\/pdf\">pdf<\/a>]<\/li>\n<li>S.K. Mustikovela, V. Jampani, S. De Mello, S. Liu, U. Iqbal, C. Rother, J. Kautz (2020). &#8220;Self-Supervised Viewpoint Learning from Image Collections&#8221;, CVPR 2020. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2020\/04\/ssv_cvpr20.pdf\">pdf<\/a>]<\/li>\n<li>A. Bhowmik, S. Gumhold, C. Rother, E. Brachmann, &#8220;Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task&#8221;, CVPR 2020 (oral). [<a href=\"https:\/\/arxiv.org\/pdf\/1912.00623.pdf\">pdf<\/a>]<\/li>\n<li>F. Kluger, E. Brachmann, H. Ackermann, C .Rother, M.Y. Yang, B. Rosenhahn, &#8220;CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus&#8221;, CVPR 2020. [<a href=\"https:\/\/arxiv.org\/pdf\/2001.02643.pdf\">pdf<\/a>] [<a href=\"https:\/\/github.com\/fkluger\/consac\">project page<\/a>]<\/li>\n<li>C. Kamann, C. Rother, &#8220;Benchmarking the Robustness of Semantic Segmentation Models&#8221;, CVPR 2020. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2020\/04\/kamann2020benchmarking.pdf\">pdf<\/a>]<\/li>\n<li>S. Haller, M. Prakash, L. Hutschenreiter, T. Pietzsch, C. Rother, F. Jug, P. Swoboda, B. Savchynskyy, &#8220;A Primal-Dual Solver for Large-Scale Tracking-by-Assignment&#8221;, AISTATS 2020. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/stefan_haller\/pdf\/A%20Primal-Dual%20Solver%20for%20Large-Scale%20Tracking-by-Assignment%20-%20AISTATS2020.pdf\">pdf<\/a>] [<a href=\"https:\/\/vislearn.github.io\/libct\/\">project website<\/a>]<\/li>\n<li>S. Tourani, A. Shekhovtsov, C. Rother, B. Savchynskyy, &#8220;Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization&#8221;, AISTATS 2020. [<a href=\"\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/tourani-taxonomy-of-dual-BCA-methods-for-discrete-energy-minimization--AISTATS2020.pdf\">pdf<\/a>]<\/li>\n<li>A. Krull, P. Hirsch, C. Rother, A. Schiffrin, C. Krull (2020). &#8220;Artificial-intelligence-driven scanning probe microscopy&#8221;,\u00a0Communications Physics volume 3, 54. [<a href=\"https:\/\/www.nature.com\/articles\/s42005-020-0317-3\">link<\/a>]<\/li>\n<li>S. Wolf, A. Bailoni, C. Pape, N. Rahaman, A. Kreshuk, U. K\u00f6the, F.A. Hamprecht (2020), &#8220;The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning&#8221;. IEEE Transactions on Pattern Analysis and Machine Intelligence 2020. [<a href=\"https:\/\/dx.doi.org\/10.1109\/TPAMI.2020.2980827\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/1904.12654.pdf\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2019<\/strong><\/p>\n<ul>\n<li>T. Adler, L. Ayala, L. Ardizzone, H. Kenngott, A. Vemuri, B. Muller-Stich, C. Rother, U. K\u00f6the, L. Maier-Hein, &#8220;Out of Distribution Detection for Intra-Operative Functional Imaging&#8221;, MICCAI UNSURE Workshop 2019. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2019\/adler2019ood.pdf\">pdf<\/a>]<\/li>\n<li>J. Kleesiek, J.N. Morshuis, F. Isensee, K. Deike-Hofmann, D. Paech, P. Kickingereder, U. K\u00f6the, C. Rother, M. Forsting, W. Wick, M. Bendszus, H.-P. Schlemmer, A. Radbruch, &#8220;Can Virtual Contrast Enhancement in Brain MRI Replace Gadolinium?&#8221;, Investigative Radiology October 2019. [<a href=\"https:\/\/journals.lww.com\/investigativeradiology\/Abstract\/2019\/10000\/Can_Virtual_Contrast_Enhancement_in_Brain_MRI.6.aspx\" target=\"_blank\" rel=\"noopener\">journal<\/a>]<\/li>\n<li>T. Leistner, H. Schilling, R. Mackowiak, S. Gumhold, C. Rother, &#8220;Learning to Think Outside the Box: Wide-Baseline Light-Field Depth Estimation from Low-Baseline Training Data&#8221;, 3DV 2019 (oral). [<a href=\"https:\/\/arxiv.org\/pdf\/1909.09059.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/learning-think-outside-box-wide-baseline-light-field-depth-estimation-epi-shift\/\">project page<\/a>]<\/li>\n<li>C. Kamann, C. Rother, &#8220;Benchmarking the Robustness of Semantic Segmentation Models&#8221;, Arxiv 2019. [<a href=\"https:\/\/arxiv.org\/abs\/1908.05005\">pdf<\/a>]<\/li>\n<li>E. Brachmann, C. Rother, &#8220;Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses&#8221;, ICCV 2019. [<a href=\"https:\/\/arxiv.org\/pdf\/1905.04132.pdf\">pdf<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/neural-guided-ransac\/\">project page<\/a>]<\/li>\n<li>E. Brachmann, C. Rother, &#8220;Expert Sample Consensus Applied to Camera Re-Localization&#8221;, ICCV 2019. [<a href=\"https:\/\/arxiv.org\/pdf\/1908.02484.pdf\">pdf<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#ICCV19\">project page<\/a>]<\/li>\n<li>L. Ardizzone, C. L\u00fcth, J. Kruse, C. Rother, U. K\u00f6the, &#8220;Guided Image Generation with Conditional Invertible Neural Networks&#8221;, GCPR 2020, arXiv:1907.02392, [<a href=\"https:\/\/arxiv.org\/abs\/1907.02392\">arxiv<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2019\/ardizzone2019guided.pdf\">pdf<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2019\/ardizzone2019guided_supplement.pdf\">supplement<\/a>]<\/li>\n<li>J. Kruse, L. Ardizzone, C. Rother, U. K\u00f6the, &#8220;Benchmarking Invertible Architectures on Inverse Problems&#8221;, First Workshop on Invertible Neural Networks and Normalizing Flows, ICML 2019. [<a href=\"https:\/\/arxiv.org\/abs\/2101.10763\">arxiv<\/a>] [<a href=\"https:\/\/arxiv.org\/pdf\/2101.10763\" target=\"blank\" rel=\"noopener\">pdf<\/a>]<\/li>\n<li>T.-G. Nguyen, L. Ardizzone, U. Koethe (2019). &#8220;Training Invertible Neural Networks as Autoencoders&#8221;, GCPR 2019, Springer LNCS 11824, arXiv:2303.11239. [<a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-33676-9_31\">link<\/a>], [<a href=\"https:\/\/arxiv.org\/abs\/2303.11239\">arxiv<\/a>], [<a href=\"https:\/\/arxiv.org\/pdf\/2303.11239\">pdf<\/a>]<\/li>\n<li>W. Li, O. Hosseini Jafari, C. Rother, &#8220;Localizing Common Objects Using Common Component Activation Map&#8221;, Explainable AI Workshop, CVPR 2019 [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2019\/Li2019CVPR.pdf\">pdf<\/a>]<\/li>\n<li>T. J. Adler, L. Ardizzone, A. Vemuri, L. Ayala, J. Gr\u00f6hl, T. Kirchner, S. Wirkert, J. Kruse, C. Rother, U. K\u00f6the, L. Maier-Hein, &#8220;Uncertainty-Aware Performance Assessment of Optical Imaging Modalities with Invertible Neural Networks&#8221;, IPCAI 2019 [<a href=\"https:\/\/arxiv.org\/abs\/1903.03441\">arxiv<\/a>]<\/li>\n<li>Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollar, &#8220;Panoptic Segmentation&#8221;, CVPR 2019, [<a href=\"https:\/\/arxiv.org\/abs\/1801.00868\">arxiv<\/a>]<\/li>\n<li>L. Ardizzone, J. Kruse, S. Wirkert, D. Rahner, E.W. Pellegrini, R.S. Klessen, L. Maier-Hein, C. Rother, U. K\u00f6the, &#8220;Analyzing Inverse Problems with Invertible Neural Networks&#8221;, ICLR 2019 [<a href=\"https:\/\/arxiv.org\/abs\/1808.04730\">arxiv<\/a>] [<a href=\"https:\/\/openreview.net\/forum?id=rJed6j0cKX\">OpenReview<\/a>] [<a href=\"https:\/\/openreview.net\/pdf?id=rJed6j0cKX\">pdf<\/a>]<\/li>\n<li>S. Berg, D. Kutra, &#8230;, U. K\u00f6the, F.A. Hamprecht, A. Kreshuk (2019): &#8220;ilastik: interactive machine learning for (bio)image analysis&#8221;, Nature Methods, vol. 16, pages 1226\u20131232 [<a href=\"https:\/\/www.nature.com\/articles\/s41592-019-0582-9\">link<\/a>]<\/li>\n<\/ul>\n<p><strong>2018<\/strong><\/p>\n<ul>\n<li>H. Abu Alhaija, S.K. Mustikovela, A. Geiger, C. Rother, &#8220;Geometric Image Synthesis&#8221;, ACCV 2018 [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2018\/Alhaija2018ACCV.pdf\">pdf<\/a>] [<a href=\"https:\/\/youtu.be\/W2tFCz9xJoU\">video<\/a>]<\/li>\n<li>O. Hosseini Jafari*, S.K. Mustikovela*, K. Pertsch, E. Brachmann, C. Rother, &#8220;iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects&#8221;, ACCV 2018 [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2018\/iPose.pdf\">pdf<\/a>] (*equal contribution)<\/li>\n<li>W. Li*, O. Hosseini Jafari*, C. Rother, &#8220;Deep Object Co-Segmentation&#8221;, ACCV 2018 [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2018\/DOCS.pdf\">pdf<\/a>] (*equal contribution)<\/li>\n<li><span class=\"this-person\">R. Mackowiak<\/span>, P. Lenz, O. Ghori, F. Diego, O. Lange, C. Rother, &#8220;<span class=\"title\">CEREALS &#8211; Cost-Effective REgion-based Active Learning for Semantic Segmentation&#8221;,<\/span> BMVC 2018. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2018\/09\/CEREALS.pdf\">pdf<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2018\/09\/CEREALS_supp.pdf\">supp<\/a>]<\/li>\n<li>S. Tourani, A. Shekhovtsov, C. Rother, B.Savchynskyy, &#8220;MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models&#8221;, ECCV 2018. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2014\/08\/eccv2018submission.pdf\" target=\"_blank\" rel=\"noopener\">pdf<\/a>]<\/li>\n<li>T. Hodan, F. Michel, E. Brachmann, W. Kehl, A. Glent Buch, D. Kraft, B. Drost, J. Vidal, S. Ihrke, X. Zabulis, C. Sahin, F. Manhardt, F. Tombari, T. Kim, J. Matas, C. Rother, &#8220;BOP: Benchmark for 6D Object Pose Estimation&#8221;, ECCV 2018. <a href=\"https:\/\/arxiv.org\/pdf\/1808.08319v1.pdf\">[pdf]<\/a><\/li>\n<li>H. Abu Alhaija, S.K. Mustikovela, L. Mescheder, A. Geiger, C. Rother, &#8220;Augmented Reality Meets Computer Vision Efficient Data Generation for Urban Driving Scenes&#8221;, IJCV 2018. [<a href=\"https:\/\/link.springer.com\/article\/10.1007\/s11263-018-1070-x\">link<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2018\/Alhaija2018IJCV.pdf\">pdf<\/a>]<\/li>\n<li>E. Brachmann, C. Rother, &#8220;Learning Less is More &#8211; 6D Camera Localization via 3D Surface Regression&#8221;, CVPR 2018. [<a href=\"https:\/\/arxiv.org\/pdf\/1711.10228.pdf\">pdf<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#CVPR18\">project page<\/a>]<\/li>\n<li>H. Schilling, M. Diebold, C. Rother, B. J\u00e4hne, &#8220;Trust your Model: Light Field Depth Estimation with inline Occlusion Handling&#8221;, CVPR 2018. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2018\/04\/CVPR2018_4110_Schilling.pdf\">pdf<\/a>]<\/li>\n<li>S. Haller, P. Swoboda, B. Savchynskyy, &#8220;Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation&#8221;, AAAI 2018. [<a href=\"\/vislearn\/HTML\/people\/stefan_haller\/pdf\/aaai2018.pdf\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2017<\/strong><\/p>\n<ul>\n<li>A. Arnab, S. Zheng, S. Jayasumana, B. Romera-Paredes, M. Larsson, A. Kirillov, B. Savchynskyy, C. Rother, F. Kahl, P.H.S. Torr, &#8220;Conditional Random Fields meet Deep Neural Networks for Semantic Segmentation&#8221;, IEEE Signal Processing Magazine, Special Issue in Deep Learning for Visual Understanding, White Paper, 2017. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2017\/CRFMeetCNN4SemanticSegmentation.pdf\">pdf<\/a>]<\/li>\n<li>H. Abu Alhaija , S. K. Mustikovela, L. Mescheder, A. Geiger, C. Rother, &#8220;Augmented Reality Meets Deep Learning for Car Instance Segmentation in Urban Scenes&#8221;, BMVC 2017. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2017\/Alhaija2017BMVC.pdf\">pdf<\/a>][<a href=\"https:\/\/arxiv.org\/pdf\/1708.01566.pdf\">extended Arxiv pdf<\/a>]<\/li>\n<li>W. Li, O. Hosseini Jafari, C. Rother, &#8221;Semantic-Aware Image Smoothing&#8221;, VMV 2017. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2014\/08\/paper1024_CRC.pdf\">pdf<\/a>]<\/li>\n<li>J. Kruse, C. Rother, U. Schmidt, &#8220;Learning to Push the Limits of Efficient FFT-based Image Deconvolution&#8221;, ICCV 2017. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2017\/09\/iccv17kruse.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2017\/09\/iccv17kruse_sup.pdf\">supp<\/a>]<\/li>\n<li>A. Behl*, O. Hosseini Jafari*, S. K. Mustikovela*, H. Abu Alhaija, C. Rother, A. Geiger, &#8220;Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?&#8221;, ICCV 2017. [<a href=\"\/vislearn\/HTML\/publications\/papers\/2017\/instancesceneflow.pdf\">pdf<\/a>][<a href=\"\/vislearn\/HTML\/publications\/papers\/2017\/instancesceneflow-supp.pdf\">supp<\/a>] (*equal contribution)<\/li>\n<li>S. Ramos, S. Gehrig, P. Pinggera, U. Franke, C. Rother. &#8220;Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling.&#8221; , Intelligent Vehicles Symposium (IV) (oral). [<a href=\"https:\/\/arxiv.org\/pdf\/1612.06573v1.pdf\">pdf<\/a>]<\/li>\n<li>E. Brachmann, A. Krull, S. Nowozin, J. Shotton, F. Michel, S. Gumhold, C. Rother, &#8220;DSAC \u2013 Differentiable RANSAC for Camera Localization&#8221;, CVPR 2017 (oral). [<a href=\"https:\/\/arxiv.org\/pdf\/1611.05705.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#DSAC\">project page<\/a>]<\/li>\n<li>P. Swoboda, J. Kuske, B. Savchynskyy, &#8220;A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems&#8221;, CVPR 2017. [<a href=\"https:\/\/arxiv.org\/pdf\/1612.05460\">pdf<\/a>]<\/li>\n<li>P. Swoboda, C. Rother, H. Abu Alhaija, D. Kainmueller, B. Savchynskyy, &#8220;A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching&#8221;, CVPR 2017. [<a href=\"https:\/\/arxiv.org\/pdf\/1612.05476\">pdf<\/a>]<\/li>\n<li>A. Kirillov, E. Levinkov, B. Andres, B. Savchynskyy, C. Rother, &#8220;InstanceCut: from Edges to Instances with MultiCut&#8221;, CVPR 2017. <a href=\"\/vislearn\/HTML\/people\/alexander_kirillov\/publications\/instancecut.pdf\">[pdf]<\/a><\/li>\n<li>F. Michel, A. Kirillov, E. Brachmann, A. Krull, S. Gumhold, B. Savchynskyy, C. Rother, &#8220;Global Hypothesis Generation for 6D Object Pose Estimation&#8221;, CVPR 2017. [<a href=\"https:\/\/arxiv.org\/pdf\/1612.02287.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#GLOB\">project page<\/a>]<\/li>\n<li>E. Levinkov, J. Uhrig, S. Tang, M. Omran, E. Insafutdinov, A. Kirillov, C. Rother, T. Brox, B. Schiele, B. Andres, &#8220;Joint Graph Decomposition &amp; Node Labeling: Problem, Algorithms, Applications&#8221;, CVPR 2017. <a href=\"\/vislearn\/HTML\/people\/alexander_kirillov\/publications\/graph_decomposition.pdf\">[pdf]<\/a><\/li>\n<li>A. Krull, E. Brachmann, S. Nowozin, F. Michel, J. Shotton, C. Rother, &#8220;PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning&#8221;, CVPR 2017. [<a href=\"https:\/\/arxiv.org\/pdf\/1612.03779.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#AGENT\">project page<\/a>]<\/li>\n<li>D. Massiceti, A. Krull, E. Brachmann, C. Rother, P.H.S. Torr, &#8220;Random Forests versus Neural Networks \u2212 What\u2019s Best for Camera Localization?&#8221;, ICRA 2017. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/alexander_krull\/publications\/ICRA_2017.pdf\">pdf<\/a>]<\/li>\n<li>D. Schlesinger, F. Jug, G. Myers, C. Rother, D. Kainm\u00fcller, &#8220;Crowd Sourcing Image Segmentation with iaSTAPLE&#8221;, ISBI 2017. [<a href=\"\/vislearn\/HTML\/people\/dmitrij_schlesinger\/publications\/isbi2017.pdf\">pdf<\/a>]<\/li>\n<li>O. Hosseini Jafari, O. Groth, A. Kirillov, M. Y. Yang, C. Rother, &#8220;Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation&#8221;, ICRA 2017. [<a href=\"https:\/\/arxiv.org\/pdf\/1702.08009.pdf\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2016<\/strong><\/p>\n<ul>\n<li>S. K. Mustikovela, M. Y. Yang, C. Rother, &#8220;Can Ground Truth Label Propagation from Video help Semantic Segmentation?&#8221;, Video Segmentation Workshop, ECCV 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/siva_mustikovela\/publications\/label_prop_helps_segmentation_eccvw16.pdf\">pdf<\/a>]<\/li>\n<li>P. Pinggera, S. Ramos, S. Gehrig, U. Franke, C. Rother, R. Mester, \u201cLost and Found: Detecting Small Road Hazards for Self-Driving Vehicles\u201d, IROS 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/carsten_rother\/publications\/papers\/IROS_camera_ready.pdf\">pdf<\/a>]<\/li>\n<li>A. Kirillov, A. Shekhovtsov, C. Rother, B. Savchynskyy, &#8220;Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization&#8221;, NIPS 2016. <a href=\"http:\/\/arxiv.org\/pdf\/1606.07015v2\">[pdf]<\/a><\/li>\n<li>A. Kirillov, D. Schlesinger, S. Zheng, B. Savchynskyy, P.H.S. Torr, C. Rother, &#8220;Joint Training of Generic CNN-CRF Models with Stochastic Optimization&#8221;, ACCV 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/Kirillov-ACCV2016-CNN-CRF.pdf\">pdf<\/a>]<\/li>\n<li>J.H. Kappes, P. Swoboda, B. Savchynskyy, T. Hazan, C. Schn\u00f6rr, &#8220;Multicuts and Perturb &amp; MAP for Probabilistic Graph Clustering&#8221;, in J. Math. Imag. Vision 2016. <a href=\"https:\/\/arxiv.org\/pdf\/1601.02088.pdf\">[pdf]<\/a> [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/bib\/Kappes-perturbed-multicut-JMIV2016.bib\">bib<\/a>]<\/li>\n<li>P. Swoboda, A. Shekhovtsov, J.H. Kappes, C. Schn\u00f6rr, B. Savchynskyy, &#8220;Partial Optimality by Pruning for MAP-Inference with General Graphical Models&#8221;, in IEEE Trans. Patt. Anal. Mach. Intell., vol. 38, July 2016, pp. 1370-1382. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/swoboda-GraphicalModelsPersistency-PAMI2016.pdf\">preprint<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/bib\/swoboda-GraphicalModelsPersistency-PAMI2016.bib\">bib<\/a>]<\/li>\n<li>A. Sellent, C. Rother, S. Roth,&#8221;Stereo Video Deblurring&#8221;, ECCV 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2016\/2016-eccv-sellent-stereo_video_deblurring-preprint.pdf\">pdf<\/a>][<a href=\"http:\/\/download.visinf.tu-darmstadt.de\/papers\/2016-eccv-sellent-stereo_video_deblurring-supplemental.pdf\">supp<\/a>]<\/li>\n<li>D. L. Richmond, D. Kainmueller, M. Y. Yang, E. W. Myers, C. Rother, &#8220;Mapping Auto-context Decision Forests to Deep ConvNets for Semantic Segmentation&#8221;, BMVC 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/carsten_rother\/publications\/papers\/richmondBMVC16.pdf\">pdf<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/carsten_rother\/publications\/papers\/richmondBMVC16supp.pdf\">supplement<\/a>] <a href=\"https:\/\/arxiv.org\/pdf\/1507.07583.pdf\">[Extended Arxiv pdf]<\/a><\/li>\n<li>L. A. Royer, D. L. Richmond, C. Rother, B. Andres, D. Kainmueller, &#8220;Convexity Shape Constraints for Image Segmentation&#8221;, CVPR 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/carsten_rother\/publications\/papers\/ConvexSegm.pdf\">pdf<\/a>]<\/li>\n<li>J. Mund, F. Michel, F. Dieke-Meier, H. Fricke, L. Meyer, C. Rother, &#8220;Introducing LiDAR Point Cloud-based Object Classification for Safer Apron Operations&#8221;, ESAVS 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2016\/Introducing LiDAR Point Cloud-based Object Classification for Safer Apron Operations - Mund- ESAVS 2016.pdf\">pdf<\/a>]<\/li>\n<li>E. Brachmann, F. Michel, A. Krull, M. Y. Yang, S. Gumhold, C. Rother, &#8220;Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image&#8221;, CVPR 2016. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2016\/Brachmann_Uncertainty-Driven_6D_Pose_CVPR_2016_paper.pdf\" target=\"_blank\" rel=\"noopener\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2017\/11\/cvpr16_uncertainty_supp.pdf\" target=\"_blank\" rel=\"noopener\">supplement<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#CVPR16\">project page<\/a>]<\/li>\n<li>F. Matulic, W. <span class=\"st\">B\u00fcschel,<\/span> M. Y. Yang, S. Ihrke, A. Ramraika, C. Rother, R. Dachselt, &#8220;Smart Ubiquitous Projection: Discovering Surfaces for the Projection of Adaptive Content&#8221;, Proceedings of the 34th Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems, 2016. <a href=\"http:\/\/delivery.acm.org\/10.1145\/2900000\/2892545\/ea2592-matulic.pdf?ip=129.206.118.27&amp;id=2892545&amp;acc=ACTIVE%20SERVICE&amp;key=2BA2C432AB83DA15%2E4992EA3396EC4E12%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&amp;__acm__=1536582594_9bb4a6e4e161c211e18cd59478556a25\">[pdf]<\/a><\/li>\n<li>O. Hosseini Jafari, M. Y. Yang, &#8220;Real-Time RGB-D based Template Matching Pedestrian Detection&#8221;, ICRA 2016. [<a href=\"\/vislearn\/HTML\/people\/omid_hosseini\/publications\/realPD_ICRA16.pdf\">pdf<\/a>]<\/li>\n<\/ul>\n<p><strong>2015<\/strong><\/p>\n<ul>\n<li>A. Kirillov, D. Schlesinger, D. Vetrov, C. Rother, B. Savchynskyy, &#8220;M-Best-Diverse Labelings for Submodular Energies and Beyond&#8221;, NIPS 2015. [<a href=\"\/vislearn\/HTML\/people\/alexander_kirillov\/publications\/mbest_submodular_nips15.pdf\">pdf with supplementary material<\/a>][<a href=\"\/vislearn\/HTML\/people\/alexander_kirillov\/publications\/bib\/kirillov-nips2015.bib\">bib<\/a>]<\/li>\n<li>A. Krull, E. Brachmann, F. Michel, M. Y. Yang, S. Gumhold, C. Rother, &#8220;Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images&#8221;, ICCV 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/alexander_krull\/publications\/Krull2015.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#ICCV15\">project page<\/a>]<\/li>\n<li>A. Kirillov, B. Savchynskyy, D. Schlesinger, D. Vetrov, C. Rother, &#8220;Inferring M-Best Diverse Solutions in a Single One&#8221;, ICCV 2015. [<a href=\"\/vislearn\/HTML\/people\/alexander_kirillov\/publications\/mbest_iccv15.pdf\">pdf with supplementary material<\/a>][<a href=\"\/vislearn\/HTML\/people\/alexander_kirillov\/publications\/bib\/kirillov-iccv2015.bib\">bib<\/a>][<a href=\"https:\/\/youtu.be\/rWBRrUM4oLA\">video spotlight<\/a>]<\/li>\n<li>R. Nair, A. Fitzgibbon, D. Kondermann, C. Rother. &#8220;Reflection Modelling for Passive Stereo&#8221;, ICCV 2015. <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2015\/ReflectionModellingPassiveStereo.pdf\">[pdf]<\/a><\/li>\n<li>H. Abu Alhaija, A. Sellent, D. Kondermann, C. Rother, &#8220;GraphFlow &#8211; 6D Large Displacement Scene Flow via Graph Matching&#8221;, German Conference on Pattern Recognition (GCPR, a.k.a. DAGM), 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/image-matching\/graphflow\/\">project<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/hassan_abualhaija\/publications\/GraphFlow.pdf\">pdf<\/a>]<\/li>\n<li>M. Cheng, V. Prisacariu, S. Zheng, P. Torr, C Rother, &#8220;DenseCut: Densely Connected CRFs for Realtime GrabCut&#8221;, Computer Graphics Forum (CGF), 2015 (oral &amp; journal). [<a href=\"http:\/\/mmcheng.net\/densecut\/\">Project<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2015\/DenseCut.pdf\">pdf<\/a>][<a href=\"http:\/\/mftp.mmcheng.net\/Papers\/DenseCut.txt\">bib<\/a>][<a href=\"http:\/\/mmcheng.net\/code-data\/\">code<\/a>]<\/li>\n<li>S. Zheng, V. Prisacariu, M Averkiou, M. Cheng, N. Mitra, J. Shotton, P. Torr, C. Rother. \u201cObject Proposal Estimation in Depth Images using Compact 3D Shape Manifolds\u201d, German Conference on Pattern Recognition (GCPR, a.k.a. DAGM), 2015. (oral). [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2015\/ProposalEstimationUsing3Dshapemanifold_GCPR2015.pdf\">pdf<\/a>]<\/li>\n<li>J. Mund, A. Zouhar, L. Meyer, H. Fricke, C. Rother, &#8220;Performance Evaluation of LiDAR Point Clouds towards Automated FOD Detection on Airport Aprons&#8221;, ATACCS 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/carsten_rother\/publications\/papers\/Mund_ATACCS_2015_FINAL_jm240715.pdf\">pdf<\/a>]<\/li>\n<li>F. Michel, A. Krull, E. Brachmann, M. Y. Yang, S. Gumhold, C. Rother, &#8220;Pose Estimation of Kinematic Chain Instances via Object Coordinate Regression&#8221;, BMVC 2015. [<a href=\"http:\/\/www.bmva.org\/bmvc\/2015\/papers\/paper181\/index.html\" target=\"_blank\" rel=\"noopener\">pdf<\/a>][<a href=\"http:\/\/www.bmva.org\/bmvc\/2015\/papers\/paper181\/sup181.zip\" target=\"_blank\" rel=\"noopener\">Supplementary_Material<\/a>][<a href=\"http:\/\/www.bmva.org\/bmvc\/2015\/papers\/paper181\/abstract181.pdf\" target=\"_blank\" rel=\"noopener\">Extended_Abstract<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/iccv2015-articulation-challenge\/\">Dataset<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#BMVC15\">project page<\/a>]<\/li>\n<li>D. Richmond, D. Kainmueller, B. Glocker, C. Rother, G. Myers, &#8220;Uncertainty-driven Forest Predictors for Vertebra Localization and Segmentation&#8221;, MICCAI 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/carsten_rother\/publications\/papers\/richmond-MICCAI-2015-uncertaintyDrivenForest.pdf\">pdf<\/a>]<\/li>\n<li>A. Zouhar, C. Rother, S. Fuchs, &#8220;Semantic 3-D Labeling of ear implants using a global parametric transition prior&#8221;, MICCAI 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/alexander_zouhar\/publications\/zouhar-MICCAI-2015-semantic3Dlabeling.pdf\">pdf<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/alexander_zouhar\/publications\/EarData__MICCAI2015.rar\">Ear data set<\/a>]<\/li>\n<li>U. Schmidt, J. Jancsary, S. Nowozin, S. Roth, C. Rother, \u201cCascades of regression tree fields for image restoration\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence 2015. [<a href=\"http:\/\/arxiv.org\/abs\/1404.2086\">pdf<\/a>]<\/li>\n<li>W. Huang, X. Gong, M. Ying Yang, &#8220;Joint object segmentation and depth upsampling&#8221;, Signal Processing Letters, 22(2):192\u2013196, 2015. <a href=\"http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=6891185\">[link]<\/a><\/li>\n<li>Schelten, S. Nowozin, J. Jancsary, C. Rother, and S. Roth, \u201cInterleaved regression tree field cascades for blind image deconvolution\u201d, in <em>IEEE Winter Conference on Applications of Computer Vision (WACV)<\/em>, Waikoloa Beach, HI, Jan. 2015, pp. 494-501. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2015\/schelten-wacv-preprint.pdf\">preprint<\/a>]<\/li>\n<li>J.H. Kappes, B. Andres, F.A. Hamprecht, C. Schn\u00f6rr, S. Nowozin, D. Batra, S. Kim, T. Kroeger, B.X. Kausler, J. Lellmann, N. Komodakis, B. Savchynskyy, C. Rother, &#8220;A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems&#8221;, IJCV 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/bib\/kappes-Benchmark-IJCV2015-preprint.bib\">bib<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/kappes-Benchmark-IJCV2015-preprint.pdf\">preprint<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/kappes-Benchmark-IJCV2015-preprint-supplement1.pdf\">supplementary material 1<\/a>] [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/kappes-Benchmark-IJCV2015-preprint-supplement2.pdf\">supplementary material 2<\/a>]<\/li>\n<li>A. Shekhovtsov, P. Swoboda, B. Savchynskyy, &#8220;Maximum Persistency via Iterative Relaxed Inference with Graphical Models&#8221;, CVPR 2015. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/bib\/shekhovtsov-persistency-cvpr2015.bib\">bib<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/shekhovtsov-persistence-cvpr2015.pdf\">pdf with supplementary material]<\/a><\/li>\n<li>J. Kappes, P. Swoboda, B. Savchynskyy, T. Hazan, C. Schn\u00f6rr, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/kappes-ssvm15-multicut-perturb-and-map.pdf\">&#8220;Probabilistic Correlation Clustering and Image Partitioning Using Perturbed Multicuts&#8221;, <\/a>SSVM 2015 &#8211; oral presentation. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/bib\/kappes-ssvm15-multicut-perturb-and-map.bib\">bib<\/a>][<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/people\/bogdan\/publications\/papers\/kappes-ssvm15-multicut-perturb-and-map.pdf\">pdf]<\/a><\/li>\n<\/ul>\n<p><strong>2014<\/strong><\/p>\n<ul>\n<li>F. Besse, C. Rother, A.W. Fitzgibbon, J. Kautz, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2015\/05\/BesseIJCV.pdf\">&#8220;PMBP: PatchMatch Belief Propagation for Correspondence Field Estimation&#8221;<\/a>, International Journal of Computer Vision 110(1): 2-13, 2014.<\/li>\n<li>A. Krull, F. Michel, E. Brachmann, S. Gumhold, S. Ihrke, C. Rother, <a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-319-16817-3_25\">&#8220;6-DOF Model Based Tracking via Object Coordinate Regression<\/a>&#8220;, ACCV 2014. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#ACCV14\">project page<\/a>]<\/li>\n<li>F. Jug, T. Pietzsch, D. Kainm\u00fcller, J. Funke, M. Kaiser, E. van Nimwegen, C. Rother, G. Myers, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2014\/Jug_MM_BAMBI2014.pdf\">Optimal Joint Segmentation and Tracking of Escherichia Coli in the Mother Machine<\/a>&#8220;, <a href=\"http:\/\/bambi.cs.ucl.ac.uk\/index.html\">BAMBI@MICCAI 2014<\/a>.<\/li>\n<li>M. Hornacek, F. Besse, J. Kautz, A. Fitzgibbon, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2014\/Hornacek_PMflow.pdf\">Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation<\/a>&#8220;, ECCV 2014.<\/li>\n<li>P. M\u00e1rquez-Neila, P. Kohli, C. Rother, L. Baumela, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2014\/NHRF_ECCV14.pdf\">Non-parametric Higher-order Random Fields for Image Segmentation&#8221;<\/a>, ECCV 2014.<\/li>\n<li>E. Brachmann, A. Krull, F. Michel, S. Gumhold, J. Shotton, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-content\/uploads\/2017\/11\/eccv14_6dpose.pdf\">Learning 6D Object Pose Estimation using 3D Object Coordinates&#8221;<\/a>, ECCV 2014. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/research\/scene-understanding\/pose-estimation\/#ECCV14\">project page<\/a>]<\/li>\n<li>D. Kainmueller, F. Jug, C. Rother, G. Myers, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2014\/finalMICCAI2014.pdf\">&#8220;Active Graph Matching for Automatic Joint Segmentation and Annotation of C. elegans<\/a>&#8220;, <a href=\"http:\/\/miccai2014.org\/\">MICCAI 2014<\/a>.<\/li>\n<li>S. Zheng, M. Cheng, J. Warrell, P. Sturgess, V. Vineet, C. Rother, P. H. S. Torr, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2014\/denseseg4objatt_CVPR2014_Kyle.pdf\">&#8220;Dense Semantic Image Segmentation with Objects and Attributes<\/a>&#8220;, CVPR 2014. [<a href=\"http:\/\/kylezheng.org\/papers\/szheng_denseattributes_CVPR2014.bib\">bib<\/a>][<a href=\"https:\/\/wwwpub.zih.tu-dresden.de\/\/kylezheng.org\/denseseg\/\">Project<\/a>]<\/li>\n<li>M. Hornacek, A. Fitzgibbon, C. Rother, &#8220;SphereFlow: 6 DoF Scene Flow from RGB-D Pairs&#8221;, CVPR 2014. [<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2014\/sphereflow-paper.pdf\">paper<\/a>, <a href=\"https:\/\/www.ims.tuwien.ac.at\/people\/michael-hornacek\/downloads\/sphereflow-footnote.pdf\">suppl. material<\/a>]<\/li>\n<\/ul>\n<p><strong>2013<\/strong><\/p>\n<ul>\n<li>M. Hoai, L. Torresani, F. De la Torre, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/PR13_hoai_torresani_torre_rother.pdf\">Learning discriminative localization from weakly labeled data&#8221;<\/a>, Pattern Recognition, vol. 47\/3, 2014, 1523-1534.<\/li>\n<li>V. Vineet, C. Rother, P.H.S. Torr, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/nips13_vinett_torr_rother.pdf\">&#8220;Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation&#8221;<\/a>, NIPS 2013.<\/li>\n<li>J. Kappes, B. Andres, F. Hamprecht, C. Schnoerr, S. Nowozin, D. Batra, S. Kim, B. Kausler, J. Lellmann, N. Komodakis, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/kappesetalCVPR13.pdf\">A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems&#8221;<\/a>, CVPR 2013.<\/li>\n<li>M. Hornacek, C. Rhemann, M. Gelautz, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/HornacekEtLaCVPR2013.pdf\">Depth Super Resolution by Rigid Body Self-Similarity in 3D&#8221;<\/a>, CVPR 2013.<\/li>\n<li>J. Jancsary, S. Nowozin, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/jancsary_icml_2013.pdf\">Learning Convex QP Relaxations for Structured Prediction&#8221;<\/a>, ICML 2013.<\/li>\n<li>U. Schmidt, C. Rother, S. Nowozin, J. Jancsary, S. Roth, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/schmidt2013deblurring.pdf\">Discriminative Non-blind Deblurring<\/a>&#8220;, CVPR 2013, Best Student Paper Award.<\/li>\n<li>S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, P. Kohli, &#8220;Decision Tree Fields: An Efficient Non-parametric Random Field Model for Image Labeling, in Decision Forests for Computer Vision and Medical Image Analysis&#8221;, Springer, 2013.<\/li>\n<li>L. Torresani, V. Kolmogorov, C. Rother, <a href=\"http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=6197199\">&#8220;A Dual Decomposition Approach to Feature Correspondence&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2013\/ttp2012990069s.pdf\">suppl. material<\/a>, PAMI 2013.<\/li>\n<\/ul>\n<p><strong>2012<\/strong><\/p>\n<ul>\n<li>J. Jancsary, S. Nowozin, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/jancsary2012nonparametriccrf.pdf\">Non-parametric CRFs for Image Labeling&#8221;<\/a>, NIPS Workshop on Modern Nonparametric Methods in Machine Learning, 2012.<\/li>\n<li>M. Bleyer, C. Rhemann, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/SenceProp.pdf\">Extracting 3D Scene-consistent Object Proposals and Depth from Stereo Images<\/a>&#8220;, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/SenceProp_SupMat.pdf\">sup.Material<\/a>, ECCV 2012.<\/li>\n<li>J. Jancsary, S. Nowozin, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/jancsary2012eccv.pdf\">Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/jancsary2012eccv-suppmat.pdf\">sup.Material&#8221;<\/a>, 12th European Conference on Computer Vision, 2012.<\/li>\n<li>J. Jancsary, S. Nowozin, T. Sharp, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/jancsary2012rtf.pdf\">Regression Tree Fields &#8211; An Efficient, Non-parametric Approach to Image Labeling Problems&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/jancsary2012rtf-supp.pdf\">sup.Material<\/a>, CVPR 2012.<\/li>\n<li>A. Shekhovtsov, P. Kohli, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/ShapeInpaint_DAGM.pdf\">&#8220;Curvature Prior for MRF-based Segmentation and Shape Inpainting&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/curvature_patterns-2011-TR-ar.pdf\">Tech.Report<\/a>, DAGM 2012.<\/li>\n<li>V. Lempitsky, A. Blake, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/jmiv_bnm_final.pdf\">Branch-and-Mincut: Global Optimization for Image Segmentation with High-Level Priors&#8221;<\/a>, JMIV 2012.<\/li>\n<li>A. Hosni, C. Rhemann, M. Bleyer, C. Rother, M. Gelautz, <a href=\"http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=5995372\">&#8220;Fast Cost-Volume Filtering for Visual Correspondence and Beyond&#8221;<\/a>, PAMI 2012.<\/li>\n<li>P. Kohli, C. Rother, &#8220;Higher-Order Models in Computer Vision, in Image Processing and Analysis with Graphs&#8221;, CRC Press, 2012.<\/li>\n<li>S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, P. Kohli, &#8220;Decision Tree Fields: An Efficient Non-Parametric Random Field Model for Image Labelling, in Decision Forests: for Computer Vision and Medical Image Analysis&#8221;, Springer: Advances in Computer Vision and Pattern Recognition, 2012.<\/li>\n<li>F. Besse, C. Rother, A. Fitzgibbon, J. Kautz, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/PMBP.pdf\">&#8220;PMBP: PatchMatch Belief Propagation for Correspondence Field Estimation&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/PMPBPsupmat.pdf\">sup.Material<\/a>, BMVC &#8211; Best Industrial Impact Prize award, 2012.<\/li>\n<li>P. Kohli, H. Nickisch, C. Rother, C. Rhemann, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/User-CentricLearning_2012.pdf\">&#8220;User-centric Learning and Evaluation of Interactive Segmentation Systems&#8221;<\/a>, IJCV 2012.<\/li>\n<li>M. Sindeev, A. Konushin, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/AlphaFlow.pdf\">&#8220;Alpha flow for video matting&#8221;<\/a>, ACCV 2012.<\/li>\n<li>S. Meister, S. Izadi, P. Kohli, M. H\u00e4mmerle, C. Rother, D. Kondermann, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2012\/IROS2012_final.pdf\">&#8220;When Can We Use KinectFusion for Ground Truth Acquisition?&#8221;<\/a>, Workshop on Color-Depth Camera Fusion in Robotics, IROS, 2012.<\/li>\n<\/ul>\n<p><strong>2011<\/strong><\/p>\n<ul>\n<li>A. Mansfield, M. Prasad, C. Rother, T. Sharp, P. Kohli, L. Van Gool, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/152963\">&#8220;Transforming Image Completion&#8221;<\/a>, BMVC 2011.<\/li>\n<li>A. Criminisi, T. Sharp, C. Rother, P. Perez, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/ACriminisi_ACM_TOG2010.pdf\">&#8220;Geodesic Image and Video Editing&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/Criminisi_ACM_TOG2010_Video_LowRes.wmv\">Win Video<\/a>, Invited talk at SIGGRAPH, 2011, Vancouver. Published in ACM Transactions on Graphics, 2011.<\/li>\n<li>C. Rhemann, A. Hosni, M. Bleyer, C. Rother, M. Gelautz, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/rhemannEtAl.pdf\">&#8220;Fast Cost-Volume Filtering for Visual Correspondence and Beyond&#8221;<\/a>, <a href=\"https:\/\/www.ims.tuwien.ac.at\/publications\/tuw-202088\">see also<\/a>, CVPR 2011.<\/li>\n<li>S. Vicente, C. Rother, V. Kolmogorov, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/ObjectCosegmentation_CVPR11.pdf\">Object Cosegmentation&#8221;<\/a>, CVPR 2011.<\/li>\n<li>K. He, C. Rhemann, C. Rother, X. Tang, J. Sun, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/HeEtAl.pdf\">&#8220;A Global Sampling Method for Alpha Matting<\/a>&#8220;, CVPR 2011.<\/li>\n<li>M. Bleyer, C. Rother, P. Kohli, D. Scharstein, S. Sinha, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/BleyerAtAl.pdf\">Object Stereo &#8211; Joint Stereo Matching and Object Segmentation&#8221;<\/a>, CVPR 2011.<\/li>\n<li>C. Rother, P. Kohli, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/RotherKohli-SparseHigherOrder.pdf\">&#8220;Sparse Higher Order Functions of Discrete Variables &#8212; Representation and Optimization&#8221;<\/a>, no. MSR-TR-2011-45, April 2011.<\/li>\n<li>C. Rother, V. Kolmogorov, Y. Boykov, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/RotherEtAlMRFBook-GrabCut.pdf\">Interactive Foreground Extraction using graph cut&#8221;<\/a>, no. MSR-TR-2011-46, March 2011.<\/li>\n<li>P. Pletscher, S. Nowozin, P. Kohli, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/map_back_on_map.pdf\">&#8220;Putting MAP back on the map&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/SupMat_map_back_on_map.pdf\">sup.Material<\/a>, DAGM 2011.<\/li>\n<li>M. Bleyer, C. Rhemann, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/PatchMatchStereo_BMVC2011_6MB.pdf\">PatchMatch Stereo &#8211; Stereo Matching with Slanted Support Windows&#8221;<\/a>, in BMVC, 2011.<\/li>\n<li>S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, P. Kohli, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/DTF.pdf\">Decision Tree Fields&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/SupMatDTF.pdf\">sup.Material<\/a>, ICCV 2011.<\/li>\n<li>P. Gehler, C. Rother, M. Kiefel, L. Zhang, B. Schoelkopf, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2011\/nips11intrinsic.pdf\">Recovering Intrinsic Images with a Global Sparsity&#8221;<\/a>, <a href=\"http:\/\/people.tuebingen.mpg.de\/mkiefel\/projects\/intrinsic\/\">see also<\/a>, NIPS 2011.<\/li>\n<\/ul>\n<p><strong>2010<\/strong><\/p>\n<ul>\n<li>E. Toeppe, M. Oswald, D. Cremers, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/toeppe_et_al_accv10.pdf\">&#8220;Image-based 3D modeling via Cheeger sets<\/a>&#8220;, ACCV 2010, HONORABLE MENTION.<\/li>\n<li>H. Nickisch, C. Rother, P. Kohli, C. Rhemann, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/final_iasyslearn.pdf\">Learning an Interactive Segmentation System<\/a>&#8220;, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/final_iasyslearn_supp.pdf\">sup.Material<\/a>, BEST PAPER AWARD, ICVGIP 2010.<\/li>\n<li>M. Bleyer, C. Rother, P. Kohli, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/SurfaceStereo_CVPR2010.pdf\">Surface Stereo with Soft Segmentation&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/SurfaceStereo_CVPR2010_supmat.pdf\">sup.Material<\/a>, CVPR 2010.<\/li>\n<li>C. Rhemann, C. Rother, P. Kohli, M. Gelautz, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/PSF-basedPriorAlphaMatting.pdf\">&#8220;A Spatially Varying PSF-based Prior for Alpha Matting<\/a>&#8220;, CVPR 2010.<\/li>\n<li>V. Gulshan, C. Rother, A. Criminisi, A. Blake, A. Zisserman, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/FinalPaper.pdf\">&#8220;Geodesic Star Convexity for Interactive Image Segmentation&#8221;<\/a>, <a href=\"http:\/\/www.robots.ox.ac.uk\/%7Evgg\/research\/iseg\/#Evaluation\">see also<\/a>, CVPR 2010.<\/li>\n<li>V. Lempitsky, C. Rother, S. Roth, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/fusionPAMI.pdf\">Fusion Moves for Markov Random Field Optimization&#8221;<\/a>, TPAMI, vol. 32, no. 8, pp. 1392-1405, 2010.<\/li>\n<li>P. Kohli, V. Lempitsky, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/Multi-Scale-Optim-DAGM2010.pdf\">&#8220;Uncertainty Driven Multi-Scale Optimization&#8221;<\/a>, DAGM 2010.<\/li>\n<li>B. Glocker, H. Heibel, N. Navab, P. Kohli, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/HOlikelihood_eccv2010.pdf\">TriangleFlow: Optical Flow with Triangulation-based Higher-Order Likelihoods&#8221;<\/a>, ECCV 2010.<\/li>\n<li>A. Mansfield, P. Gehler, L. Van Gool, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/sceneCarving_ECCV2010.pdf\">Scene Carving: Scene Consistent Image Retargeting&#8221;<\/a>, ECCV 2010.<\/li>\n<li>A. Mansfield, P. Gehler, L. Van Gool, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/Alex_ECCVworkshop.pdf\">&#8220;Visibility Maps for Improving Seam Carving&#8221;<\/a>, Media Retargeting Workshop, ECCV 2010.<\/li>\n<li>S. Vicente, V. Kolmogorov, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2010\/Cosegmentation_ECCV2010.pdf\">&#8220;Cosegmentation Revisited: Models and Optimization&#8221;<\/a>, ECCV 2010.<\/li>\n<\/ul>\n<p><strong>2009<\/strong><\/p>\n<ul>\n<li>V. Lempitsky, C. Rother, S. Roth, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/fusion.pdf\">Fusion Moves for Markov Random Field Optimization&#8221;<\/a>, no. MSR-TR-2009-60, May 2009.<\/li>\n<li>D. Singaraju, C. Rother, C. Rhemann, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-matting-newModels.pdf\">New Appearance Models for Image Matting&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-matting-newModels_supMat.pdf\">sup.Material<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-matting-newModels-TR.pdf\">Tech.Report<\/a>, CVPR 2009.<\/li>\n<li>C. Rother, P. Kohli, W. Feng, J. Jia, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-HoSparse.pdf\">Minimizing Sparse Higher Order Energy Functions of Discrete Variables&#8221;<\/a>, CVPR 2009.<\/li>\n<li>J. Shotton, J. Winn, C. Rother, A. Criminisi, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/ijcv07a.pdf\">TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context&#8221;<\/a>, IJCV 2009.<\/li>\n<li>A. Shesh, A. Criminisi, C. Rother, G. Smyth, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/OOB-final.pdf\">&#8220;3D-aware Image Editing for Out of Bounds Photography&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/OOB-supplementary-final.pdf\">sup.Material<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/GraphicsInterface_Video102.mov\">QuickTime movie<\/a>, <a href=\"http:\/\/research.microsoft.com\/en-us\/projects\/i3l\/i3l_oob.aspx\">see also<\/a>, Graphics Interface 2009.<\/li>\n<li>V. Lempitsky, P. Kohli, C. Rother, T. Sharp, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/iccv2009_ImSegBoundingBoxPrior.pdf\">Image Segmentation with A Bounding Box Prior&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/iccv2009_ImSegBoundingBoxPrior_TR.pdf\">Tech.Report<\/a>, in ICCV, 2009.<\/li>\n<li>M.H. Nguyen, L. Torresani, F. de la Torre, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/SegSVM_ICCV09.pdf\">Weakly supervised discriminative localization and classification: a joint learning process&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/SegSVM_CMU-RI-TR-09-29.pdf\">Tech.Report<\/a>, in ICCV, 2009.<\/li>\n<li>C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli, P. Rott, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-matting-Eval.pdf\">&#8220;A Perceptually Motivated Online Benchmark for Image Matting&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-matting-Eval_supMat.pdf\">sup.Material<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cvpr09-matting-Eval_TR.pdf\">Tech.Report<\/a>, in CVPR, 2009.<\/li>\n<li>S. Roth, V. Lempitsky, C. Rother, &#8220;Discrete-Continuous Optimization for Optical Flow Estimation&#8221;, in Statistical and Geometrical Approaches to Visual Motion Analysis, vol. LNCS vol. 5604, pp. 1-22,Springer Verlag, 2009.<\/li>\n<li>S. Vicente, V. Kolmogorov, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/ICCV2009.pdf\">&#8220;Joint optimization of segmentation and appearance models&#8221;<\/a>, ICCV 2009.<\/li>\n<li>O.J. Woodford, C. Rother, V. Kolmogorov, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/cert_1536_final.pdf\">A Global Perspective on MAP Inference for Low-Level Vision&#8221;<\/a>, in ICCV, 2009.<\/li>\n<li>M. Bleyer, M. Gelautz, C. Rother, C. Rhemann, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2009\/CVPR09_StereoMatting.pdf\">A Stereo Approach that Handles the Matting Problem via Image Warping&#8221;<\/a>, in CVPR, 2009.<\/li>\n<\/ul>\n<p><strong>2008<\/strong><\/p>\n<ul>\n<li>L. Torresani, V. Kolmogorov, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/eccv08-MatchingMRF.pdf\">&#8220;Feature Correspondence via Graph Matching: Models and Global Optimization&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/TR-2008-101.pdf\">Tech.Report<\/a>, in ECCV, October 2008.<\/li>\n<li>A. Rav-Acha, P. Kohli, C. Rother, A.W. Fitzgibbon, <a href=\"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1399504.1360616\">&#8220;Unwrap Mosaics: A new representation for video editing&#8221;<\/a>, SIGGRAPH 2008, vol. 27, no. 3, Association for Computing Machinery, August 2008.<\/li>\n<li>V. Lempitsky, S. Roth, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/CVPR08-FusionFlow.pdf\">&#8220;Fusion Flow:Discrete-Continuous Optimization for Optical Flow Estimation&#8221;<\/a>, CVPR 2008.<\/li>\n<li>R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/Szeliski-PAMI08.pdf\">&#8220;A Comparative Study of Energy Minimization Methods for Markov RandomFields with Smoothness-Based Priors&#8221;<\/a>, <a href=\"http:\/\/vision.middlebury.edu\/MRF\/\">see also<\/a>, TPAMI, vol. 30, no.6, pp. 1068-1080, 2008.<\/li>\n<li>C. Rhemann, C. Rother, A. Rav-Acha, T. Sharp, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/Matting_CVPR08.pdf\">High Resolution Matting via Interactive Trimap Segmentation&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/Matting_CVPR08_supMaterial.pdf\">sup.Material<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/Matting_CVPR08_TR.pdf\">Tech.Report<\/a>, in CVPR, June 2008.<\/li>\n<li>P. Kohli, A. Shekhovtsov, C. Rother, V. Kolmogorov, P.H. S. Torr, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/icml08-PartOptMRF.pdf\">&#8220;On partial optimality in multi-label MRFs&#8221;<\/a>, Proceedingsof International Conference on Machine Learning, 2008.<\/li>\n<li>V. Lempitsky, A. Blake, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/eccv2008-BranchMinCut.pdf\">Image Segmentation by Branch-and-Mincut&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/eccv2008-BranchMinCut-TR.pdf\">Tech.Report<\/a>, ECCV 2008.<\/li>\n<li>C. Rhemann, C. Rother, M. Gelautz, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/BMVC08-Matting.pdf\">&#8220;Improving Color Modeling for Alpha Matting&#8221;<\/a>, BMVC 2008.<\/li>\n<li>S. Vicente, V. Kolmogorov, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/CVPR08-ConnectedGC.pdf\">&#8220;Graph cut based image segmentation with connectivity Priors&#8221;<\/a>, CVPR 2008.<\/li>\n<li>P. Gehler, C. Rother, A. Blake, T. Minka, T. Sharp, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2008\/CVPR08-ColorConst.pdf\">Bayesian Color Constancy Revisited&#8221;<\/a>, <a href=\"http:\/\/files.is.tue.mpg.de\/pgehler\/projects\/color\/\">see also<\/a>, in CVPR, 2008.<\/li>\n<\/ul>\n<p><strong>2007<\/strong><\/p>\n<ul>\n<li>V. Kolmogorov, Y. Boykov, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/iccv07-ParaMaxFlow.pdf\">Applications of parametric maxflow in computer Vision&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/iccv07-ParaMaxFlow-TR.pdf\">Tech.Report<\/a>, in ICCV, October 2007.<\/li>\n<li>C. Rother, V. Kolmogorov, V. Lempitsky, M. Szummer, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/cvpr07-QPBOpi.pdf\">&#8220;Optimizing Binary MRFs via Extended Roof Duality&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/cvpr07-QPBOpi-TR.pdf\">Tech.Report<\/a>, CVPR 2007.<\/li>\n<li>A. Kannan, J. Winn, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/LearnedJigsaw_NIPS2006.pdf\">Clustering appearance and shape by learning jigsaws&#8221;<\/a>, Advances in Neural Information Processing Systems, MIT Press, 2007.<\/li>\n<li>J.F. Lalonde, D. Hoiem, A.A. Efros, J. Winn, C. Rother, A. Criminisi, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/criminisi_siggraph_07.pdf\">Photo Clip Art&#8221;<\/a>, Proc. ACM SIGGRAPH, 2007.<\/li>\n<li>A. Criminisi, J. Shotton, A. Blake, C. Rother, P.H.S. Torr, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/Criminisi_ijcv2006.pdf\">Efficient Dense Stereo with Occlusion for New View-Synthesis by Four-State Dynamic Programming&#8221;<\/a>, IJCV 2007.<\/li>\n<li>D. Hoeim, C. Rother, J. Winn, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/3dLayoutCRF_Hoiem_Rother_Winn_CVPR2007.pdf\">&#8220;3D Layout CRF for Multi-View Object Class Recognition and Segmentation&#8221;<\/a>, CVPR 2007.<\/li>\n<li>V. Lempitsky, C. Rother, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/iccv07-LogCut.pdf\">LogCut- Efficient Graph Cut Optimization for Markov Random Fields<\/a>&#8220;, in ICCV, 2007.<\/li>\n<li>V. Kolmogorov, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/PAMI07-QPBO.pdf\">Minimizing non-submodular functions with graph cuts &#8211; a review&#8221;<\/a>, PAMI,vol. 29, no. 7, 2007.<\/li>\n<li>A.J. Sellen, A. Fogg, M. Aitken, S. Hodges, C. Rother, K. Wood, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2007\/CHI07_SensecamMemory.pdf\">Do Life-Logging Technologies Support Memory for the Past? An Experimental Study Using SenseCam&#8221;<\/a>, inCHI, 2007.<\/li>\n<\/ul>\n<p><strong>2006<\/strong><\/p>\n<ul>\n<li>C. Rother, L. Bordeaux, Y. Hamadi, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/autocollage_rotheretal_siggraph2006.pdf\">AutoCollage&#8221;<\/a>, in ACM Transactions on Graphics (SIGGRAPH), 2006.<\/li>\n<li>C. Rother, V. Kolmogorov, T. Minka, A. Blake, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/CVPR06-CoSeg.pdf\">&#8220;Cosegmenting Image Pairs by Matching Global Histograms&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/CVPR06-CoSeg-TR.pdf\">Tech.Report<\/a>, CVPR 2006.<\/li>\n<li>V. Kolmogorov, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/eccv06-compHighConMRF.pdf\">Comparison of energy minimization algorithms for highly connected Graphs&#8221;<\/a>, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/eccv06-compHighConMRF-TR.pdf\">Tech.Report<\/a>, ECCV 2006.<\/li>\n<li>R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/szsvkatr-eccv06.pdf\">&#8220;A Comparative Study of Energy Minimization Methods for Markov RandomFields&#8221;<\/a>, ECCV 2006.<\/li>\n<li>D.S. Kirk, A.J. Sellen, C. Rother, K.R. Wood, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/paper_chi06_photowork.pdf\">&#8220;Understanding Photowork&#8221;<\/a>, Proceedings of CHI Conference on Human Factorsin Computing Systems, Associationfor Computing Machinery, 2006.<\/li>\n<li>A. Kannan, J. Winn, C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/NIPS06-Jigsaw.pdf\">Clusteringappearance and shape by learning jigsaws&#8221;<\/a>, NIPS 2006.<\/li>\n<li>J. Shotton, J. Winn, C. Rother, A. Criminisi, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/textonboost_eccv2006.pdf\">&#8220;TextonBoost:Joint Appearance, Shape and Context Modeling for Mulit-Class Object Recognition and Segmentation&#8221;<\/a>, ECCV 2006.<\/li>\n<li>V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2006\/Criminisi_pami2006.pdf\">&#8220;Probabilistic fusion of stereo with color and contrast for bi-layer Segmentation&#8221;<\/a>, in PAMI, MSR-TR-2005-35, pp. 18, January 2006.<\/li>\n<\/ul>\n<p><strong>2005<\/strong><\/p>\n<ul>\n<li>V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2005\/StereoSegmentation_tr.pdf\">&#8220;Probabilistic fusion of stereo with color and contrast for video Segmentation&#8221;<\/a>, no. MSR-TR-2005-36, March 2005.<\/li>\n<li>V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2005\/criminisi_cvpr2005.pdf\">&#8220;Bi-layer segmentation of binocular stereo Video<\/a>&#8220;, Proc. CVPR. Winner of BEST PAPER HONORABLE MENTION AWARD, 2005.<\/li>\n<li>C. Rother, S. Kumar, V. Kolmogorov, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2005\/CVPR05-Tapestry.pdf\">Digital Tapestry&#8221;<\/a>, CVPR 2005.<\/li>\n<li>A. Blake, A. Criminisi, G. Cross, V. Kolmogorov, Carsten Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2005\/Criminisi_isrr2005.pdf\">&#8220;Fusion of stereo, color and contrast&#8221;<\/a>, ISRR 2005.<\/li>\n<\/ul>\n<p><strong>2004<\/strong><\/p>\n<ul>\n<li>C. Rother, V. Kolmogorov, A. Blake, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2004\/siggraph04-grabcut.pdf\">GrabCut-Interactive Foreground Extraction using Iterated Graph Cuts<\/a>&#8220;, ACM Transactions onGraphics (SIGGRAPH), 2004.<\/li>\n<li>A. Blake, C. Rother, M. Brown, P. Perez, P. Torr, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2004\/eccv04-GMMRF.pdf\">&#8220;Interactive Image Segmentation using an adaptive GMMRF model&#8221;<\/a>, ECCV 2004.<\/li>\n<\/ul>\n<p><strong>2003<\/strong><\/p>\n<ul>\n<li>C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2003\/ssab03-transCam.pdf\">Linear Multi-View Reconstruction for Translating Cameras&#8221;<\/a>, SSAB 2003.<\/li>\n<li>C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2003\/iccv03_linReconst.pdf\">Linear Multi-View Reconstruction of Points, Lines, Planes and Cameras, using a Reference Plane&#8221;<\/a>, ICCV 2003.<\/li>\n<li>C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2003\/thesis.pdf\">Multi-View Reconstruction and Camera Recovery using a Real or Virtual Reference Plane; PHD THESIS&#8221;<\/a>, January 2003.<\/li>\n<li>A. Criminisi, J. Shotton, A. Blake, C. Rother, P.H.S. Torr, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2003\/criminisi_techrep2003-59.pdf\">Efficient Dense Stereo and Novel-view Synthesis for Gaze Manipulation One-to-one Teleconferencing&#8221;<\/a>, MSR-TR-2003-59, 2003.<\/li>\n<\/ul>\n<p><strong>2002<\/strong><\/p>\n<ul>\n<li>C. Rother, Stefan Carlsson, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2002\/eccv02-linReconst.pdf\">&#8220;Linear Multi View Reconstruction with Missing Data&#8221;<\/a>, ECCV 2002.<\/li>\n<li>C. Rother, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2002\/ivc02-vanPoint.pdf\">A new Approach for Vanishing Point Detection in Architectural Environments<\/a>&#8220;, in Journal Image and Vision Computing (IVC; Special Issue on BMVC 2000), vol. 20, no. 9-10,pp. 647-656, 2002.<\/li>\n<li>C. Rother, Stefan Carlsson, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2002\/ijcv02-linReconst.pdf\">&#8220;Linear Multi View reconstruction and Camera Recovery using a Reference Plane&#8221;<\/a>, in Int. Journal Computer Vision (IJCV; Special Issue on Multi-View Modeling and Rendering of Visual Scenes), vol. 49, no. 2\/3, pp. 117-141, 2002.<\/li>\n<li>C. Rother, Stefan Carlsson, D. Tell, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2002\/icpr02-projFact.pdf\">Projective Factorization of Planes and Cameras in Multiple Views&#8221;<\/a>, ICPR 2002.<\/li>\n<\/ul>\n<p><strong>2001<\/strong><\/p>\n<ul>\n<li>C. Rother, S. Carlsson, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2001\/iccv01-linReconst.pdf\">MultiView reconstruction and Camera Recovery&#8221;<\/a>, ICCV 2001.<\/li>\n<\/ul>\n<p><strong>2000<\/strong><\/p>\n<ul>\n<li>C. Rother, <a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2000\/ivc02-vanpoint.pdf\">&#8220;A new Approach for Vanishing Point Detection in Architectural Environments&#8221;<\/a>, in BMVC 2000.<\/li>\n<li>C. Rother, H.-H. Nagel, &#8220;<a href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/HTML\/publications\/papers\/2000\/ssab00-tracking.pdf\">Analysing the Localisation of Road Vehicles for Tracking&#8221;<\/a>, SSAB 2000.<\/li>\n<\/ul>\n<p><strong>1999<\/strong><\/p>\n<ul>\n<li>C. Rother, &#8220;Analyse initialer Positionssch\u00e4tzungen bei der Bildfolgenauswertung&#8221;, DAGM 1999.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Note, we add all peer reviewed articles to this\u00a0list, and sometimes\u00a0also arXiv papers (but not all arXiv papers). Books B. Savchynskyy Discrete Graphical Models &#8211; An Optimization Perspective Text-book. Now Publishers, Special Issue on Foundations and Trends in Computer Graphics and Vision, 2019. [pdf with a tech. report formatting] &#8220;Markov Random Fields for Vision and [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"inline_featured_image":false,"footnotes":""},"class_list":["post-127","page","type-page","status-publish","hentry","post"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Publications - Computer Vision and Learning Lab Heidelberg<\/title>\n<meta name=\"description\" content=\"Publications of members of the Computer Vision and Learning Lab Heidelberg.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Publications - Computer Vision and Learning Lab Heidelberg\" \/>\n<meta property=\"og:description\" content=\"Publications of members of the Computer Vision and Learning Lab Heidelberg.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/\" \/>\n<meta property=\"og:site_name\" content=\"Computer Vision and Learning Lab Heidelberg\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-05T16:30:49+00:00\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"30 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/publications\\\/\",\"url\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/publications\\\/\",\"name\":\"Publications - Computer Vision and Learning Lab Heidelberg\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/#website\"},\"datePublished\":\"2014-08-30T20:24:49+00:00\",\"dateModified\":\"2025-11-05T16:30:49+00:00\",\"description\":\"Publications of members of the Computer Vision and Learning Lab Heidelberg.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/publications\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/publications\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/publications\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Publications\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/#website\",\"url\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/\",\"name\":\"Computer Vision and Learning Lab Heidelberg\",\"description\":\"Computer Vision and Learning Lab Heidelberg\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/hci.iwr.uni-heidelberg.de\\\/vislearn\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Publications - Computer Vision and Learning Lab Heidelberg","description":"Publications of members of the Computer Vision and Learning Lab Heidelberg.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/","og_locale":"en_US","og_type":"article","og_title":"Publications - Computer Vision and Learning Lab Heidelberg","og_description":"Publications of members of the Computer Vision and Learning Lab Heidelberg.","og_url":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/","og_site_name":"Computer Vision and Learning Lab Heidelberg","article_modified_time":"2025-11-05T16:30:49+00:00","twitter_misc":{"Est. reading time":"30 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/","url":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/","name":"Publications - Computer Vision and Learning Lab Heidelberg","isPartOf":{"@id":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/#website"},"datePublished":"2014-08-30T20:24:49+00:00","dateModified":"2025-11-05T16:30:49+00:00","description":"Publications of members of the Computer Vision and Learning Lab Heidelberg.","breadcrumb":{"@id":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/publications\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/"},{"@type":"ListItem","position":2,"name":"Publications"}]},{"@type":"WebSite","@id":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/#website","url":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/","name":"Computer Vision and Learning Lab Heidelberg","description":"Computer Vision and Learning Lab Heidelberg","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/pages\/127","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/comments?post=127"}],"version-history":[{"count":254,"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/pages\/127\/revisions"}],"predecessor-version":[{"id":5358,"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/pages\/127\/revisions\/5358"}],"wp:attachment":[{"href":"https:\/\/hci.iwr.uni-heidelberg.de\/vislearn\/wp-json\/wp\/v2\/media?parent=127"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}