TY - GEN
T1 - A Decomposition Model for Stereo Matching
AU - Yao, Chengtang
AU - Jia, Yunde
AU - Di, Huijun
AU - Li, Pengxiang
AU - Wu, Yuwei
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of stereo matching at the original resolution, our model only runs dense matching at a very low resolution and uses sparse matching at different higher resolutions to recover the disparity of lost details scale-by-scale. After the decomposition of stereo matching, our model iteratively fuses the sparse and dense disparity maps from adjacent scales with an occlusion-aware mask. A refinement network is also applied to improving the fusion result. Compared with high-performance methods like PSMNet and GANet, our method achieves 10 - 100× speed increase while obtaining comparable disparity estimation results.
AB - In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of stereo matching at the original resolution, our model only runs dense matching at a very low resolution and uses sparse matching at different higher resolutions to recover the disparity of lost details scale-by-scale. After the decomposition of stereo matching, our model iteratively fuses the sparse and dense disparity maps from adjacent scales with an occlusion-aware mask. A refinement network is also applied to improving the fusion result. Compared with high-performance methods like PSMNet and GANet, our method achieves 10 - 100× speed increase while obtaining comparable disparity estimation results.
UR - http://www.scopus.com/inward/record.url?scp=85123223852&partnerID=8YFLogxK
U2 - 10.1109/CVPR46437.2021.00603
DO - 10.1109/CVPR46437.2021.00603
M3 - Conference contribution
AN - SCOPUS:85123223852
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 6087
EP - 6096
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PB - IEEE Computer Society
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Y2 - 19 June 2021 through 25 June 2021
ER -