Abstract

Cost aggregation is one of the key steps in the stereo matching problem. In order to improve aggregation accuracy, we propose a cost-aggregation method that can embed minimum spanning tree (MST)-based support region filtering into PatchMatch 3D label search rather than aggregating on fixed size patches. However, directly combining PatchMatch label search and MST filtering is not straightforward, due to the extremely high complexity. Thus, we develop multiple MST structures for cost aggregation on plenty of 3D labels, and design the tree-level random search strategy to find possible 3D labels of each pixel. Extensive experiments show that our method reaches higher accuracy than the other existing cost-aggregation and global-optimization methods such as the 1D MST, the PatchMatch and the PatchMatch Filter, and currently ranks first on the Middlebury 3.0 benchmark.

© 2017 Optical Society of America

Local stereo matching with adaptive shape support window based cost aggregation

Yafan Xu, Yan Zhao, and Mengqi Ji
Appl. Opt. 53(29) 6885-6892 (2014)

Cross-scale cost aggregation integrating intrascale smoothness constraint with weighted least squares in stereo matching

Hao Ma, Shunyi Zheng, Chang Li, Yingsong Li, Li Gui, and Rongyong Huang
J. Opt. Soc. Am. A 34(4) 648-656 (2017)

Approximate geodesic distance tree filter for cost aggregation

Yusheng Jin, Hong Zhao, Penghui Bu, and Jiaxing Yan
Appl. Opt. 60(30) 9578-9586 (2021)

Four-direction global matching with cost volume update for stereovision

Yusheng Jin, Hong Zhao, and Penghui Bu
Appl. Opt. 60(19) 5471-5479 (2021)

Occlusion disparity refinement for stereo matching through the geometric prior-based adaptive label search

Junwei Wang, Wei Zhou, Ziheng Qian, Jiaqi Shen, and Hanming Guo
J. Opt. Soc. Am. A 38(11) 1619-1630 (2021)