Graphics, Capture and Massively Parallel Computing
The main focus of our research interest is the development of digitization methods for all aspects of the real world. This includes capturing geometry, surface color and several other attributes, e.g. reflectance properties of objects. Most of our methods perform the reconstruction solely on photographs that have been taken under controlled conditions (such as constant lighting and known camera parameters). Our latest developments, however, are capable of dealing with photos taken under uncontrolled conditions, for example images from community photo collections such as flickr.
Beyond that, we are interested in massively parallel computing to exploit the full potential of nowadays graphics hardware to solve computationally expensive problems in various areas, for example visual computing and bio informatics.
PhD Defense Michael Waechter
Michael Waechter successfully defended his thesis entitled “Novel View Prediction as a Quality Metric for Image-Based Modeling and Rendering” on August 18th – congrats!
Michael Goesele on Sabbatical in Winter Term 2017/18
Michael Goesele will be on sabbatical (Forschungssemester) in the winter term 2017/18, i.e., from October 2017 through March 2018. More details are available on his personal web page.
PhD Defense Sven Widmer
Sven Widmer successfully defended his thesis entitled “Foundations and Methods for GPU based Image Synthesis” on July 14th – congrats!
PhD Defense Nicolas Weber
Nicolas Weber successfully defended his thesis entitled “GPU Array Access Auto-Tuning” on June 19th – congrats!
Visibility-Consistent Thin Surface Reconstruction Using Multi-Scale Kernels
How Human Am I? EEG-based Evaluation of Animated Virtual Characters
In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, Denver, Colorado, USA, 2017
PFASUM: a substitution matrix from Pfam structural alignments
In: BMC Bioinformatics, 18(1), p.293, 2017