Speaker: Dr. Carsten Stoll, MPI Saarbrücken

Friday, March 19th, 11:15am, in BC 329

Title: Template Based Shape Processing

As computers can only represent and process discrete data, information gathered from the real world always has to be sampled. While it is nowadays possible to sample many signals accurately and thus generate high-quality reconstructions (for example of images and audio data), accurately and densely sampling 3D geometry is still a challenge. The signal samples may be corrupted by noise and outliers, and contain large holes due to occlusions. These issues become even more pronounced when also considering the temporal domain. Because of this, developing methods for accurate reconstruction of shapes from a sparse set of discrete data is an important aspect of the computer graphics processing pipeline. I will present approaches to including semantic knowledge into reconstruction processes using template based shape processing. We can formulate shape reconstruction as a deformable template fitting process, where we try to fit a given template model to the sampled data. This approach allows us to present novel solutions to several fundamental problems in the area of shape reconstruction. We can address static problems like semantically meaningful hole-filling in surface reconstruction from 3D scans, temporal problems such as mesh based performance capture, and dynamic problems like the estimation of physically based material parameters of animated templates.

Short Bio:
Carsten Stoll is a post-doctoral researcher at the Max-Planck-Institute for Informatics in Saarbrücken. He received his MSc. degree in Computer Science in 2004 from the Technical University of Darmstadt, where he worked with Prof. Marc Alexa on surface reconstruction algorithms. He then became a graduate student at the Max-Planck-Institute for Informatics in Saarbrücken under the supervision of Prof. Hans-Peter Seidel (MPII) and Dr. Christian Theobalt (Stanford University/MPII). In 2008, he was a visiting researcher at Stanford University's AI Lab with Prof. Sebastian Thrun. Carsten defended his PhD thesis about "Template Based Shape Processing" in November 2009. His research interests lie in the field of geometric modeling, markerless motion capture and combining techniques from Graphics and Vision to generate high quality virtual representation of real objects and performers. In his past time he enjoys good books, enthralling stories, electronic music and martial arts.