Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
A maximum likelihood stereo algorithm
Computer Vision and Image Understanding
A Bayesian approach to binocular stereopsis
International Journal of Computer Vision
Ill-Posed Problems and Regularization Analysis in Early Vision
Ill-Posed Problems and Regularization Analysis in Early Vision
Depth Discontinuities by Pixel-to-Pixel Stereo
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Depth from edge and intensity based stereo
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
We present a new center-referenced basis for representation of stereo correspondence that permits a more natural, complete and concise representation of matching constraints. In this basis, which contains new occlusion nodes, natural constrainsts are applied in the form of a trellis. A MAP disparity estimate is found using DP methodsin the trellis. Like other DP methods, the computational load is low, but it has the benefit of a structure is very suitable for parallel computation. Experiments are performed under varying degrees of noise quantity and maximum disparity, confirming the performance.