Welcome to the Computer Vision Lab Dresden
Computer Vision is a science that develops models and methods for understanding, analyzing, acquiring and processing images and generally high-dimensional structured data. Computer Vision is an inter-disciplinary field with strong links to Machine Learning, Optimization, Biology, Computer Graphics, and Human Computer Interaction. The mission of the Computer Vision Lab Dresden is to develop novel theoretical concepts which are practically relevant. We work on a broad range of application areas, from image matching, via semantic scene understanding, to Bio Imaging. On the theoretical side we focus on optimization and learning in probabilistic graphical models, as well as Deep Learning.
- Jakob Kruse has won the Carl Zeiss Diplompreis for his Master’s thesis on the topic “Comparison of Learned Inference Approaches …
- Ever wondered how to train a computer vision pipeline, which contains RANSAC, in an end-to-end fashion? See our project page …
- Best Science Paper Award at BMVC 16! For our joint work with Gene Myers team about Mapping Random Forests to …
- Bogdan Savchynskyy got a 3-year DFG Grant accepted on the topic of exact and efficient inference in challenging Random Fields …
- You can download the code of our CVPR 16 paper on pose estimation and camera localization here.
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.
Collaborators & Industrial Partners
We also have industrial collaborations with Daimler Research, Adobe (Seattle) and Basler AG.