We propose a novel linear method for scale invariant figure ground separation in images and videos. Figure ground separation is treated as a superpixel labeling problem. We optim...
Image based relighting techniques are a popular choice for generating photo-realistic images of objects under any lighting condition. A typical process for creating such a model i...
This paper proposes a simple “prior-free” method for solving non-rigid structure-from-motion factorization problems. Other than using the basic low-rank condition, our method ...
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...