Abstract | ||
---|---|---|
We introduce a real-time stereo matching technique based on a reformulation of Yoon and Kweon's adaptive support weights algorithm [1]. Our implementation uses the bilateral grid to achieve a speedup of 200× compared to a straightforward full-kernel GPU implementation, making it the fastest technique on the Middlebury website. We introduce a colour component into our greyscale approach to recover precision and increase discriminability. Using our implementation, we speed up spatialdepth superresolution 100×. We further present a spatiotemporal stereo matching approach based on our technique that incorporates temporal evidence in real time (14 fps). Our technique visibly reduces flickering and outperforms per-frame approaches in the presence of image noise. We have created five synthetic stereo videos, with ground truth disparity maps, to quantitatively evaluate depth estimation from stereo video. Source code and datasets are available on our project website. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-15558-1_37 | ECCV (3) |
Keywords | Field | DocType |
straightforward full-kernel gpu implementation,real-time spatiotemporal stereo,spatiotemporal stereo,dual-cross-bilateral grid,project website,stereo video,greyscale approach,per-frame approach,fastest technique,middlebury website,synthetic stereo video,real-time stereo,machine learning,real time,source code,ground truth | Computer vision,Stereo cameras,Source code,Computer science,CUDA,Image noise,Ground truth,Artificial intelligence,Machine learning,Grayscale,Grid,Speedup | Conference |
Volume | ISSN | ISBN |
6313 | 0302-9743 | 3-642-15557-X |
Citations | PageRank | References |
132 | 4.66 | 21 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Christian Richardt | 1 | 393 | 26.27 |
Douglas Orr | 2 | 132 | 4.66 |
Ian Davies | 3 | 182 | 9.84 |
Antonio Criminisi | 4 | 6801 | 394.29 |
Neil A. Dodgson | 5 | 723 | 54.20 |