Prof. Thomas Brox

Our group works intensively on deep learning. This includes new, untypical network architectures, new application domains, and ways to train such networks with less supervision.

We permanently work on improving the quality of optical flow estimation and other motion estimation methods, such as point tracking or scence flow estimation. As optical flow is the corner stone of all video analysis, we believe that even the smallest improvement has large effects on the overall performance of video related methods. In the past we made a couple of important contributions to the field, the lastest and most revolutionary one being a convolutional network that can predict high accuracy optical flow almost in real-time.

A major research focus in our group is video segmentation. One approach to video segmentation is by means of motion segmentation. Motion segmentation allows to retrieve object regions in a fully unsupervised manner. Another task is to propagate a segmentation given in one frame to the whole video. In 2014 and 2016, we co-organized a Workshop on video segmentation.