The task of 2-D articulated human pose estimation in natural images is extremely challenging due to the high level of variation in human appearance. These variations arise from di...
We present a markerless motion capture approach that reconstructs the skeletal motion and detailed time-varying surface geometry of two closely interacting people from multi-view ...
We present a novel theory for characterizing defocus blurs in multi-perspective cameras such as catadioptric mirrors. Our approach studies how multi-perspective ray geometry trans...
This paper addresses the problem of efficiently solving large-scale energy minimization problems encountered in computer vision. We propose an energy-aware method for merging ran...
Taesup Kim, Sebastian Nowozin, Pushmeet Kohli, Cha...
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...