This paper presents a unified approach to solve different bilinear factorization problems in Computer Vision in the presence of missing data in the measurements. The problem is f...
Stereo is a useful technique for obtaining depth information from images. However, it is required that the baseline length between two cameras should be large to increase depth pr...
We consider inference in a general data-driven object-based model of multichannel audio data, assumed generated as a possibly underdetermined convolutive mixture of source signals...
A review of the facts about human stereo vision leads to the conclusion that the human stereo processing mechanism is very flexible in the presence of other depth cues. Stereopsis ...
This paper investigates the benefit of dense stereo for the ROI generation stage of a pedestrian detection system. Dense disparity maps allow an accurate estimation of the camera ...