Stereo Matching Using Belief Propagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Surface Reconstruction Method Using Global Graph Cut Optimization
International Journal of Computer Vision
A progressive edge-based stereo correspondence method
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Reliable depth map regeneration via a novel omnidirectional stereo sensor
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Hi-index | 0.00 |
Several new algorithms for visual correspondence based on graph cuts have recently been developed. While these methods give very strong results in practice, they do not handle occlusions properly. Specifically, they treat the two input images asymmetrically, and they do not ensure that a pixel corresponds to at most one pixel in the other image. In this paper, we present two new methods which properly address occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our methods perform well both at detecting occlusions and computing disparities.