Sciweavers

CVPR
2004
IEEE
14 years 6 months ago
Window-Based, Discontinuity Preserving Stereo
Traditionally, the problem of stereo matching has been addressed either by a local window-based approach or a dense pixel-based approach using global optimization. In this paper, ...
Motilal Agrawal, Larry S. Davis
CVPR
2001
IEEE
14 years 6 months ago
Rectifying Transformations That Minimize Resampling Effects
Image rectification is the process of warping a pair of stereo images in order to align the epipolar lines with the scan-lines of the images. Once a pair of images is rectified, s...
Joshua Gluckman, Shree K. Nayar
IJCV
2008
282views more  IJCV 2008»
14 years 9 months ago
Stereo Matching Using Population-Based MCMC
In this paper, we propose a new stereo matching method using the population-based Markov Chain Monte Carlo (Pop-MCMC), which belongs to the sampling-based methods. Since the previo...
Wonsik Kim (Seoul National University), Joonyoung ...
CVPR
2008
IEEE
14 years 9 months ago
Illumination and Camera Invariant Stereo Matching
Color information can be used as a basic and crucial cue for finding correspondence in a stereo matching algorithm. In a real scene, however, image colors are affected by various g...
Yong Seok Heo (Seoul National University), Kyoung ...
CVPR
2009
IEEE
14 years 11 months ago
Stereo Matching with Nonparametric Smoothness Priors in Feature Space
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...
Brandon M. Smith, Hailin Jin, Li Zhang
CVPR
2009
IEEE
1930views Computer Vision» more  CVPR 2009»
14 years 11 months ago
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space
Radiometric variations between input images can seriously degrade the performance of stereo matching algorithms. In this situation, mutual information is a very popular and powe...
Yong Seok Heo (Seoul National University), Kyoung ...
CVPR
2009
IEEE
14 years 11 months ago
Stereo Matching in the Presence of Sub-Pixel Calibration Errors
Stereo matching commonly requires rectified images that are computed from calibrated cameras. Since all under- lying parametric camera models are only approximations, calibratio...
Heiko Hirschmüller, Stefan K. Gehrig