Prof. Dr. Björn Ommer

I have accepted a chair at the University of Munich. Please see my new website. My Machine Vision & Learning group's current teaching within the Computer Science department of LMU can be found there.
Full Professor for Computer Vision

Heidelberg Collaboratory for Image Processing (HCI) &
Interdisciplinary Center for Scientific Computing (IWR),
Heidelberg University

Mathematikon (INF 205), Room 4.321
HCI / IWR, Uni Heidelberg
D-69120 Heidelberg, Germany
Tel.(office): +49 6221/54-14806
Tel.(secret.): +49 6221/54-14807
Fax: +49 6221/54-14814
Email: ommer (at) uni-heidelberg (dot) de

Open PhD and PostDoc Positions in Computer Vision
Bjorn


Brief C.V.


Björn Ommer is a full professor for Scientific Computing and leads the Computer Vision Group at Heidelberg University.

He has studied computer science together with physics as a minor subject at the University of Bonn, Germany. His diploma (~M.Sc.) thesis focused on visual grouping based on perceptual organization and compositionality.

After that he pursued his doctoral studies at ETH Zurich Switzerland in the Pattern Analysis and Machine Learning Group headed by Joachim M. Buhmann. He received his Ph.D. degree from ETH Zurich in 2007 for his dissertation "Learning the Compositional Nature of Objects for Visual Recognition" which was awarded the ETH Medal.

Thereafter, Björn held a post-doc position in the Computer Vision Group of Jitendra Malik at UC Berkeley.

He serves as an associate editor for the journal IEEE T-PAMI and previously for Pattern Recognition Letters. Björn is one of the directors of the HCI and of the IWR, part of the ELLIS unit Heidelberg, principle investigator in the research training group 1653 ("Spatio/Temporal Graphical Models and Applications in Image Analysis"), and a member of the executive board and scientific committee of the Heidelberg Graduate School HGS MathComp. He has served as Area Chair for ICCV'21, CVPR'20, and ECCV'18 and organized the 2011 DAGM Workshop on Unsolved Problems in Pattern Recognition.



Research Interests


Computer vision, machine learning, cognitive science, biomedical image analysis, and the digital humanities; esp.:
semantic scene understanding, visual synthesis and interpretable AI, deep learning & self-supervision, deep metric and representation learning, object recognition in images and videos, behavior analysis, and their interdisciplinary applications.

»» Research pages

Publications


Main publications' list »» Publications of the Ommer lab

News:

2021

Blattmann, A, Milbich, T, Dorkenwald, M and Ommer, B (2021). iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis. Proceedings of the International Conference on Computer Vision (ICCV). https://arxiv.org/abs/2107.02790
Rombach, R, Esser, P and Ommer, B (2021). Geometry-Free View Synthesis: Transformers and no 3D Priors. Proceedings of the Intl. Conf. on Computer Vision (ICCV). https://arxiv.org/abs/2104.07652
Jahn, M, Rombach, R and Ommer, B (2021). High-Resolution Complex Scene Synthesis with Transformers. CVPR 2021, AI for Content Creation Workshop
Afifi, M, Derpanis, K G, Ommer, B and Brown, M S (2021). Learning Multi-Scale Photo Exposure Correction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://arxiv.org/abs/2003.11596
Esser, P, Rombach, R, Blattmann, A and Ommer, B (2021). ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis. https://arxiv.org/abs/2108.08827
Blattmann, A, Milbich, T, Dorkenwald, M and Ommer, B (2021). Understanding Object Dynamics for Interactive Image-to-Video Synthesis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://arxiv.org/abs/2106.11303v1
Dorkenwald, M, Milbich, T, Blattmann, A, Rombach, R, Derpanis, K G and Ommer, B (2021). Stochastic Image-to-Video Synthesis usin cINNs. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Roth, K, Milbich, T, Ommer, B, Cohen, J Paul and Ghassemi, M (2021). S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning. Proceedings of International Conference on Machine Learning (ICML). https://arxiv.org/abs/2009.08348
Blattmann, A, Milbich, T, Dorkenwald, M and Ommer, B (2021). Behavior-Driven Synthesis of Human Dynamics. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://arxiv.org/abs/2103.04677
Kotovenko, D, Wright, M, Heimbrecht, A and Ommer, B (2021). Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://compvis.github.io/brushstroke-parameterized-style-transfer/
Islam, M Amirul, Kowal, M, Esser, P, Jia, S, Ommer, B, Derpanis, K G and Bruce, N (2021). Shape or Texture: Understanding Discriminative Features in CNNs. International Conference on Learning Representations (ICLR)
Esser, P, Rombach, R and Ommer, B (2021). Taming Transformers for High-Resolution Image Synthesis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://arxiv.org/abs/2012.09841
Milbich, T, Roth, K, Sinha, S, Schmidt, L, Ghassemi, M and Ommer, B (2021). Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning. https://arxiv.org/abs/2107.09562
Lang, S and Ommer, B (2021). Transforming Information Into Knowledge: How Computational Methods Reshape Art History. Digital Humanities Quaterly (DHQ). 15. http://digitalhumanities.org/dhq/vol/15/3/000560/000560.html
Sanakoyeu, A, Ma, P, Tschernezki, V and Ommer, B (2021). Improving Deep Metric Learning by Divide and Conquer. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). https://arxiv.org/abs/2109.04003
Lang, S and Ommer, B (2021). Transforming Information Into Knowledge: How Computational Methods Reshape Art History. Digital Humanities Quaterly (DHQ). 15
Brattoli, B, Büchler, U, Dorkenwald, M, Reiser, P, Filli, L, Helmchen, F, Wahl, A - S and Ommer, B (2021). Unsupervised behaviour analysis and magnification (uBAM) using deep learning. Nature Machine Intelligence. https://rdcu.be/ch6pL

2020

Milbich, T, Roth, K and Ommer, B (2020). PADS: Policy-Adapted Sampling for Visual Similarity Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1. https://arxiv.org/abs/2003.11113
Esser, P, Rombach, R and Ommer, B (2020). A Note on Data Biases in Generative Models. NeurIPS 2020 Workshop on Machine Learning for Creativity and Design. https://arxiv.org/abs/2012.02516
Rombach, R, Esser, P and Ommer, B (2020). Network Fusion for Content Creation with Conditional INNs. CVPRW 2020 (AI for Content Creation). https://compvis.github.io/network-fusion/
Roth, K, Milbich, T, Sinha, S, Gupta, P, Ommer, B and Cohen, J Paul (2020). Revisiting Training Strategies and Generalization Performance in Deep Metric Learning. International Conference on Machine Learning (ICML). https://arxiv.org/pdf/2002.08473.pdf
Esser, P, Rombach, R and Ommer, B (2020). A Disentangling Invertible Interpretation Network for Explaining Latent Representations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://compvis.github.io/iin/PDF icon Article (13.07 MB)
Milbich, T, Roth, K, Bharadhwaj, H, Sinha, S, Bengio, Y, Ommer, B and Cohen, J Paul (2020). DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning. IEEE European Conference on Computer Vision (ECCV). https://arxiv.org/abs/2004.13458
Rombach, R, Esser, P and Ommer, B (2020). Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs. IEEE European Conference on Computer Vision (ECCV). https://compvis.github.io/invariances/
Rombach, R, Esser, P and Ommer, B (2020). Network-to-Network Translation with Conditional Invertible Neural Networks. Neural Information Processing Systems (NeurIPS) (Oral). https://compvis.github.io/net2net/
Lang, S and Ommer, B (2020). Das Objekt jenseits der Digitalisierung. Das digitale Objekt. 7. http://www.deutsches-museum.de/fileadmin/Content/010_DM/060_Verlag/studies-7.pdfPDF icon lang_ommer_digitalhumanities_2020_.pdf (599.56 KB)
Dorkenwald, M, Büchler, U and Ommer, B (2020). Unsupervised Magnification of Posture Deviations Across Subjects. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)PDF icon article.pdf (1.15 MB)
Braun, S, Esser, P and Ommer, B (2020). Unsupervised Part Discovery by Unsupervised Disentanglement. Proceedings of the German Conference on Pattern Recognition (GCPR) (Oral). Tübingen. https://compvis.github.io/unsupervised-part-segmentation/
Ufer, N, Lang, S and Ommer, B (2020). Object Retrieval and Localization in Large Art Collections Using Deep Multi-style Feature Fusion and Iterative Voting. IEEE European Conference on Computer Vision (ECCV), VISART Workshop PDF icon Paper (1.03 MB)
Dencker, T, Klinkisch, P, Maul, S M and Ommer, B (2020). Deep learning of cuneiform sign detection with weak supervision using transliteration alignment. PLoS ONE. 15. https://hci.iwr.uni-heidelberg.de/compvis/projects/cuneiform
Milbich, T, Roth, K, Brattoli, B and Ommer, B (2020). Sharing Matters for Generalization in Deep Metric Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). https://arxiv.org/abs/2004.05582
Milbich, T, Ghori, O and Ommer, B (2020). Unsupervised Representation Learning by Discovering Reliable Image Relations. Pattern Recognition. 102. http://arxiv.org/abs/1911.07808

2019

Brattoli, B, Roth, K and Ommer, B (2019). MIC: Mining Interclass Characteristics for Improved Metric Learning. Proceedings of the Intl. Conf. on Computer Vision (ICCV)
Lorenz, D, Bereska, L, Milbich, T and Ommer, B (2019). Unsupervised Part-Based Disentangling of Object Shape and Appearance. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Oral + Best paper finalist: top 45 / 5160 submissions)
Kotovenko, D, Sanakoyeu, A, Lang, S and Ommer, B (2019). Content and Style Disentanglement for Artistic Style Transfer. Proceedings of the Intl. Conf. on Computer Vision (ICCV)
Esser, P, Haux, J and Ommer, B (2019). Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis. Proceedings of the Intl. Conf. on Computer Vision (ICCV). https://compvis.github.io/robust-disentangling/
Ufer, N, Lui, K To, Schwarz, K, Warkentin, P and Ommer, B (2019). Weakly Supervised Learning of Dense SemanticCorrespondences and Segmentation. German Conference on Pattern Recognition (GCPR)PDF icon article (6.1 MB)
Kotovenko, D, Sanakoyeu, A, Lang, S, Ma, P and Ommer, B (2019). Using a Transformation Content Block For Image Style Transfer. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Sanakoyeu, A, Tschernezki, V, Büchler, U and Ommer, B (2019). Divide and Conquer the Embedding Space for Metric Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://github.com/CompVis/metric-learning-divide-and-conquer

2018

Bell, P and Ommer, B (2018). Computer Vision und Kunstgeschichte — Dialog zweier Bildwissenschaften. Computing Art Reader: Einführung in die digitale Kunstgeschichte, P. Kuroczyński et al. (ed.)PDF icon 413-17-83318-2-10-20181210.pdf (2.98 MB)

Pages



Selected Reports and Publications in Popular Science


"Das Objekt jenseits der Digitalisierung“, Deutsches Museum, 12/2018, The Future of the Digital Humanities beyond Digitization.

"Der Geist aus dem Computer“, Bild der Wissenschaft, 10/2018, covering part of our work in the digital humanities.

AI Learned How To Generate Human Appearance, Video on Two-Minute-Papers about our CVPR'18 paper on disentangling human behavior and appearance.

Painter AI Fools Art Historians, Video on Two-Minute-Papers about our ECCV'18 paper on artistic style transfer.

Improving Stroke Treatment Through Machine Learning, report on interdisciplinary project with neuroscientists from ETH Zurich.

Improving Motor Skills after Stroke, report on interdisciplinary project with neuroscientists from ETH Zurich.

TV documentary on our interdisciplinary work featured by RNF Television.

Björn Ommer, Bilder im Chaos, in: Universitas 68(810): 46-55, 2013.

Björn Ommer, From Chaos to Image - The Grammar of Patterns, in: Ruperto Carola Magazine, 03/2013.

Björn Ommer, Vom Pixel zum Bild - Wie Computer das Sehen lernen und die Forschungsarbeiten von Geistes- und Naturwissenschaftlern unterstützen können, in: Ruperto Carola Magazine, 02/2011.

Image Recognition: Teaching Computers to See, in: Young Talents -Innovative Ideas - Viable Alliances, 2011.

Automatische Bildanalyse - Blinde Computer sollen sehen lernen, in: Spiegel Online news report, 22.07.2011.

Dem Computer das Sehen beibringen, in: Rhein-Neckar-Zeitung newspaper article, 19.04.2010.



Teaching


Teaching Website @ University of Munich(current), Teaching Website @ Heidelberg University(outdated)


Links


Björn's new website @ University of Munich

Machine Vision & Learning Group: New website of the Ommer lab @ University of Munich

HCI @ Uni Heidelberg

Computer Vision Group @ UC Berkeley

Institute for Machine Learning @ ETH Zurich