Computer Science Colloquium: Probabilistic Morphable Models

Professor Thomas Vetter, from the University of Basel, Switzerland, will present the Department of Computer Science's colloquium, with a talk entitled, "Probabilistic Morphable Models".

The analysis of face images has many aspects reaching from face identification to social judgement  or to medical questions. In our research we aim on a single unifying approach for these tasks.  The core of our approach is an analysis by synthesis loop using a 3D morphable face model. In this talk I will extend our earlier morphable models formalism with the concept of gaussian processes. Second, I present a Data Driven Markov Cain Monte Carlo scheme for a  fitting of morphable models to  images able to integrate unreliable bottom-up cues. Based on various face image analysis tasks I will demonstrate the advantage of generative models and discuss also current limitations of our model and approach.  

Professor Thomas Vetter studied mathematics and physics and received the PhD degree in biophysics from the University of Ulm, Germany. As a postdoctoral researcher at the Center for Biological and Computational Learning at MIT, he started his research on computer vision. In 1993, he moved to the Max-Planck-Institut in Tübingen and, in 1999, he became professor of computer graphics at the University of Freiburg. Since 2002, he has been a professor of applied computer science at the University of Basel in Switzerland. His current research is on image understanding, graphics, and automated model building.

Thu, 04 Feb 2016 - 13:00

Lecture Theatre 302, Computer Science, Upper Campus, UCT.