Abstract | ||
---|---|---|
With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by consumer-level devices like smartphones, due to practical complicating factors such as thin structures, non-ideal rectification, camera module inconsistencies and various hard-case scenes. In this paper, we propose a set of innovative designs to tackle the problem of practical stereo matching: 1) to better recover fine depth details, we design a hierarchical network with recurrent refinement to update disparities in a coarse-to-fine manner, as well as a stacked cascaded architecture for inference; 2) we propose an adaptive group correlation layer to mitigate the impact of erroneous rectification; 3) we introduce a new synthetic dataset with special attention to difficult cases for better generalizing to real-world scenes. Our results not only rank 1st on both Middlebury and ETH3D benchmarks, outperforming existing state-of-the-art methods by a notable margin, but also exhibit high-quality details for real-life photos, which clearly demonstrates the efficacy of our contributions. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.01578 | IEEE Conference on Computer Vision and Pattern Recognition |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiankun Li | 1 | 0 | 0.34 |
Peisen Wang | 2 | 3 | 1.12 |
Pengfei Xiong | 3 | 0 | 1.01 |
Tao Cai | 4 | 0 | 0.34 |
Ziwei Yan | 5 | 0 | 0.34 |
Lei Yang | 6 | 0 | 0.34 |
Jiangyu Liu | 7 | 0 | 0.68 |
Haoqiang Fan | 8 | 8 | 3.13 |
Shuaicheng Liu | 9 | 21 | 4.76 |