Active Disparity Sampling for Stereo Matching With Adjoint Network

doi:10.1109/TIP.2023.3343105

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Active Disparity Sampling for Stereo Matching With Adjoint Network
	Zhang, Chenghao 1,2; Meng, Gaofeng 1,2,3; Tian, Kun 1,2; Ni, Bolin 1,2; Xiang, Shiming 1,2
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2024
卷号	33 页码:354-365
关键词	Stereo matching domain generalization active sampling adjoint network Bayesian optimization
ISSN号	1057-7149
DOI	10.1109/TIP.2023.3343105
通讯作者	Meng, Gaofeng(gfmeng@nlpr.ia.ac.cn)
英文摘要	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.
资助项目	National Natural Science Foundation of China
WOS关键词	VISION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001133501900003
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54850]
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
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.