Active Disparity Sampling for Stereo Matching With Adjoint Network

doi:10.1109/TIP.2023.3343105

	Active Disparity Sampling for Stereo Matching With Adjoint Network
	Zhang, Chenghao1,2 ; Meng, Gaofeng1,2,3 ; Tian, Kun1,2 ; Ni, Bolin 1,2; Xiang, Shiming1,2
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2024
卷号	33 页码:354-365
通讯作者	Meng, Gaofeng(gfmeng@nlpr.ia.ac.cn)
摘要	The sparse signals provided by external sources have been leveraged as guidance for improving dense disparity estimation. However, previous methods assume depth measurements to be randomly sampled, which restricts performance improvements due to under-sampling in challenging regions and over-sampling in well-estimated areas. In this work, we introduce an Active Disparity Sampling problem that selects suitable sampling patterns to enhance the utility of depth measurements given arbitrary sampling budgets. We achieve this goal by learning an Adjoint Network for a deep stereo model to measure its pixel-wise disparity quality. Specifically, we design a hard-soft prior supervision mechanism to provide hierarchical supervision for learning the quality map. A Bayesian optimized disparity sampling policy is further proposed to sample depth measurements with the guidance of the disparity quality. Extensive experiments on standard datasets with various stereo models demonstrate that our method is suited and effective in different stereo architectures and outperforms existing fixed and adaptive sampling methods under different sampling rates. Remarkably, the proposed method makes substantial improvements when generalized to heterogeneous unseen domains.
关键词	Stereo matching domain generalization active sampling adjoint network Bayesian optimization
DOI	10.1109/TIP.2023.3343105
关键词[WOS]	VISION
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001133501900003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/54851
专题	多模态人工智能系统全国重点实验室
通讯作者	Meng, Gaofeng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong 999077, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Chenghao,Meng, Gaofeng,Tian, Kun,et al. Active Disparity Sampling for Stereo Matching With Adjoint Network[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:354-365.
APA	Zhang, Chenghao,Meng, Gaofeng,Tian, Kun,Ni, Bolin,&Xiang, Shiming.(2024).Active Disparity Sampling for Stereo Matching With Adjoint Network.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,354-365.
MLA	Zhang, Chenghao,et al."Active Disparity Sampling for Stereo Matching With Adjoint Network".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):354-365.