ELLIS Munich's research in computer vision combines a number of mathematical domains including statistical inference, ML and deep neural networks, differential geometry, and continuous and discrete optimization techniques.

Computer vision is about interpreting camera data. The aim is to infer properties of the observed world from camera images or videos. The breadth of machine vision challenges is endless and the impact on society is rapidly increasing. Among the most publicly visible applications are driver assistance and autonomous mobility, biomedical image analysis and personalized medicine, earth observation from aerial, radar and satellite images, detection of anomalies in manufacturing and industrial processes, virtual and augmented reality and robotics.

ELLIS Munich's research in computer vision combines a number of mathematical domains including statistical inference, ML and deep neural networks, differential geometry, and continuous and discrete optimization techniques.

Research topics

3D reconstruction with cameras (including RGB-D cameras) and Visual SLAM (simultaneous localization and mapping)

Biomedical image and video analysis

Dynamic scene interpretation, shape analysis