“CEREALS – Cost-Effective REgion-based Active Learning for Semantic Segmentation”

Check out our paper in cooperation with the Robert Bosch GmbH. [pdf] [suppl.]

More Info

Geometric Image Synthesis

Check our new paper “Geometric Image Synthesis” [ArXiv] [video]

More Info

Robust Vision Challenge at CVPR 2018

We are happy to be involved in the organization of the Robust Vision Challenge at CVPR 2018 together with Andreas Geiger and a great team from MPI Tübingen, ETH Zurich and TU Munich. Visit http://www.robustvision.net for more information and stay tuned for details on how to participate with your stereo, flow, multi-view or segmentation algorithm!

More Info

DSAC – Differentiable RANSAC for Camera Localization

Ever wondered how to train a computer vision pipeline, which contains RANSAC, in an end-to-end fashion? See our project page or  arXiv.

More Info

Best Science Paper Award at BMVC 16!

Best Science Paper Award at BMVC 16!  For our joint work with Gene Myers team about Mapping Random Forests to Deep, sparse CNNs. Please find the paper in publications.

More Info

Accepted DFG Grant for Bogdan Savchynskyy as PI

Bogdan Savchynskyy got a 3-year DFG Grant accepted on the topic of exact and efficient inference in challenging Random Fields Models

More Info

CVPR 16 pose estimation code now online

You can download the code of our CVPR 16 paper on pose estimation and camera localization here.

More Info

New Papers accepted (NIPS, BMVC, ACCV, IROS)

New papers accepted to NIPS (on MRF diversity), BMVC (on stacked RF to CNN mapping; oral), ACCV (on new learning for CNN-CRF), and IROS (on Road Hazard detection). Please find papers in publication section.

More Info