We propose an algorithm to improve the quality of depth-maps used for Multi-View Stereo (MVS). Many existing MVS techniques make use of a two stage approach which estimates depth-m...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
Abstract. We cast the problem of motion segmentation of feature trajectories as linear manifold finding problems and propose a general framework for motion segmentation under affin...
Robust real-time tracking of non-rigid objects in a dynamic environment is a challenging task. Among various cues in tracking, color can provide an efficient visual cue for this t...
We consider the problem of continuously maintaining order sketches over data streams with a relative rank error guarantee . Novel space-efficient and one-scan randomised technique...