Computer Vision & Graphics

The Computer Vision and Graphics (CVG) group is an active research group carrying out innovative research in the field of Visual Computing. We combine extensive expertise in Computer Vision on the analysis side, i.e. capturing, sensing and understanding the visual real world and Computer Graphics on the synthesis side, i.e. modelling into digital representations and animation of these models as well as rendering and visualization, often in an analysis-by-synthesis cycle. In this context, we combine CV & CG models with deep neural networks and especially develop model-based deep learning methods, that integrate a-priori and model knowlegde into neural architectures. We develop sophisticated solutions for virtual, augmented and extended reality for a broad range of applications for industry, multimedia, medicine and security. Current topics include human shape/motion analysis and synthesis, computational video, image and video understanding, biomedical image analysis, generative models as well as augmented reality.