Visual Inference

Research

Our research lies at the intersection of computer vision and machine learning and focuses on analyzing and interpreting visual data, such as digital images and videos, with a particular emphasis on probabilistic modeling and inference. Our work is motivated by the inherent uncertainty and ambiguity of visual data and aims to model and take advantage of this uncertainty in a systematic manner. We tackle a wide variety of applications with substantial practical impact, such as image restoration, image motion estimation, detection and tracking of people in images and videos, as well as object recognition.

Teaching and Student Research

Our teaching activities include regular introductory lectures to computer vision as well as to statistical machine learning (both at the advanced Bachelor and Masters level). Moreover, we offer students the possibility of participating in the research activities of the group during Bachelor and Master thesis projects. Students who work on their thesis projects with us can expect to work on topics at the forefront of current research in visual inference and related areas. Projects that can lead to scientific publications are particularly encouraged.

Membership

Prof. Stefan Roth, Ph.D. is member of the Research Training Group Cooperative, Adaptive and Responsive Monitoring in Mixed Mode Environments