Abstract—A novel approach for reconstruction of sparse highresolution data from lower-resolution dense spatio-temporal data is introduced. The basic idea is to compute the dense ...
We propose a global optimization framework for 3D shape reconstruction from sparse noisy 3D measurements frequently encountered in range scanning, sparse featurebased stereo, and ...
Abstract. This paper presents a technique for estimating the threedimensional velocity vector field that describes the motion of each visible scene point (scene flow). The techniqu...
Andreas Wedel, Clemens Rabe, Tobi Vaudrey, Thomas ...
We present a computational framework to automatically discover high-order temporal social patterns from very noisy and sparse location data. We introduce the concept of social foo...
Feature selection for video retrieval applications is impractical with existing techniques, because of their high time complexity and their failure on the relatively sparse trainin...