Object detection is challenging partly due to the limited discriminative power of local feature descriptors. We amend this limitation by incorporating spatial constraints among ne...
Geometric reconstruction problems in computer vision can be solved by minimizing the maximum of reprojection errors, i.e., the L-norm. Unlike L2-norm (sum of squared reprojection ...
We formulate multi-view 3D shape reconstruction as the computation of a minimum cut on the dual graph of a semiregular, multi-resolution, tetrahedral mesh. Our method does not ass...
Sudipta N. Sinha, Philippos Mordohai, Marc Pollefe...
?We have recently proposed an approach to recognition that uses regions to determine the pose of objects while allowing for partial occlusion of the regions. Regions introduce an a...
We present a dynamic near-regular texture (NRT) tracking algorithm nested in a lattice-based Markov-Random-Field (MRF) model of a 3D spatiotemporal space. One basic observation use...