Computer Vision and Learning Lab
The Computer Vision and Learning Lab works in the field of Computer Vision and Machine Learning. The Lab has three groups: 3D Computer Vision (Carsten Rother), Explainable Machine Learning (Ullrich Köthe), and Optimization for Machine Learning (Bogdan Savchynskyy). Carsten Rother is head of the Lab. We work on a large range of research topics, such as 3D reconstruction, Image synthesis, Invertible Neural Networks, Explainable and Trustworthy Machine Learning, Large-scale discrete optimization, assignment and tracking. We collaborate with researchers from many other disciplines, such as computational biology, medicine, astronomy, or environmental physics. We have also been the steppingstone for successful start-ups.
Latest News
Three papers accepted to ICCV ’21, on Graph Matching; Self-supervised Object Detection; and Camera Localization
Carsten Rother among 9 most influential CV scholars in Europe
Carsten Rother was selected by aminer to be among the 9 most influential Computer Vision researchers in Europe. See: AI …Four Papers accepted to CVPR 2020
S.K. Mustikovela, V. Jampani, S. De Mello, S. Liu, U. Iqbal, C. Rother, J. Kautz “Self-Supervised Viewpoint Learning from Image …ECCV Tutorial (Half-day) on Normalizing Flow
Ullrich Köthe, Markus Brubaeker (York University/Toronto) and Carsten Rother offer a half-day tutorial at ECCV 2020 in Glasgow on “Normalizing Flows …Paper accepted to 3DV 2019
Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift [pdf] [project page]
RESEARCH HIGHLIGHTS 
The Rich Scene Model (ERC Consolidator Grant)
Given a sequence of images the goal is to recover a rich, detailed representation of the 3D world, ranging from physical to semantical aspects. To achieve this we investigate new ways to combine feature learning, modelling, physical laws, and optimization in large-scale discrete-continuous-valued probabilistic graphical model.
Our Research
Combinatorial Optimization
focusing on Graphical Models, Diversity, and Large-Scale Optimization
Read moreScene Understanding
focusing on 6D Pose estimation, Dense Matching, and Instance Recognition
Read moreSelected Events
Collaborators & Industrial Partners
Over the last years we have been collaborating with various scientific partners – such as MPI Tübingen, Oxford University, University College London, Imperial College London, ETH Zürich, Skoltech Moscow, Stanford University, TU Darmstadt, Prague University, University of Hannover, IST Vienna, TU Vienna, MPI Saarbrücken, TU Dresden, MPI-CBG and CSBD Dresden, and more.
We have also been collaborating with various industrial research labs - such as Microsoft Research Cambridge, Bejing and Redmond, Daimler, and Facebook Artificial Intelligence Researchers (FAIR).
We are part of the Heidelberg HCI 3rd phase, where we collaborate closely with Bosch.
We have also been collaborating with various industrial research labs - such as Microsoft Research Cambridge, Bejing and Redmond, Daimler, and Facebook Artificial Intelligence Researchers (FAIR).
We are part of the Heidelberg HCI 3rd phase, where we collaborate closely with Bosch.