Name
Abstract | ||
|---|---|---|
This paper provides a novel and efficient approach to dense stereo matching. The first contribution is, rather than applying disparity distribution inside a segment as hard constraint to directly project the likelihood of corresponding candidates to each pixel individually, our method treat segmentation and corresponding disparity distribution as soft constraint, and further partition each segment to sub-over segments which effectively facilitate the assumption of the disparity consistency. The second contribution is we transform this assumption into higher-order-based potential, and it can be minimized effectively through graph cut. The third contribution is the successful combination of several known techniques as one holistic framework. Two test-beds of both Middlebury and challenging real-scene data have been evaluated, results show that it obtains the state-of-the-art results while keeping efficiency. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/DICTA.2011.93 | DICTA |
Keywords | Field | DocType |
efficient approach,corresponding candidate,soft constraint,disparity distribution,disparity consistency,corresponding disparity distribution,stereo matching,robust higher-order graph cut,hard constraint,graph cut,higher-order-based potential,dense stereo matching,graph theory,higher order,estimation,test bed,minimization,visualization,statistical distributions,vectors,robustness,optimization,image segmentation,robust optimization | Cut,Graph theory,Computer vision,Pattern recognition,Computer science,Segmentation,Robustness (computer science),Image segmentation,Probability distribution,Minification,Pixel,Artificial intelligence | Conference |
Citations | PageRank | References |
1 | 0.37 | 15 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yiran Xie | 1 | 1 | 1.04 |
| Nianjun Liu | 2 | 162 | 15.01 |
| Sheng Liu | 3 | 5 | 8.58 |
| Nick Barnes | 4 | 41 | 4.42 |