Non-Isotropic Regularization of the Correspondence Space in Stereo-Vision

The correspondence problem in stereo vision is notoriously difficult. In many approaches a noisy solution is extracted from the correspondence space. Various sophisticated regularization techniques are applied then on this noisy solution. We study here the possibility to denoise the correspondence/correlation space before extracting the solution, by a non-linear and non-isotropic scheme. We show that this methods preserves edges (depth discontinuities) well and overcomes some of the problems encountered in previous approaches.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Nir A. Sochen, Rami Ben-Ari
• Keywords: Computer Vision, Correspondence Space, ICPR 2004, Noisy Solution, Sophisticated Regularization Techniques