Abstract | ||
---|---|---|
We explore the problem of real-time stereo matching on high-res imagery. Many state-of-the-art (SOTA) methods struggle to process high-res imagery because of memory constraints or speed limitations. To address this issue, we propose an end-to-end framework that searches for correspondences incrementally over a coarse-to-fine hierarchy. Because high-res stereo datasets are relatively rare, we introduce a dataset with high-res stereo pairs for both training and evaluation. Our approach achieved SOTA performance on Middlebury-v3 and KITTI-15 while running significantly faster than its competitors. The hierarchical design also naturally allows for anytime on-demand reports of disparity by capping intermediate coarse results, allowing us to accurately predict disparity for near-range structures with low latency (30ms). We demonstrate that the performance-vs-speed tradeoff afforded by on-demand hierarchies may address sensing needs for time-critical applications such as autonomous driving. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.00566 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | ISSN |
Stereo matching,Computer vision,Pattern recognition,Computer science,Artificial intelligence | Conference | 1063-6919 |
Citations | PageRank | References |
7 | 0.41 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gengshan Yang | 1 | 15 | 3.34 |
Joshua Manela | 2 | 7 | 0.41 |
Michael Happold | 3 | 7 | 0.41 |
deva ramanan | 4 | 10678 | 566.72 |