Learning Multi-View Stereo With Geometry-Aware Prior

doi:10.1109/TCSVT.2025.3578452

CSpace

	Learning Multi-View Stereo With Geometry-Aware Prior
	Chen, Kehua 1; Yuan, Zhenlong 1; Xiao, Haihong 2; Mao, Tianlu 1; Wang, Zhaoqi 1
	2025-12-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	35 期号:12 页码:12396-12409
摘要	Multi-View Stereo (MVS) reconstructs detailed 3D structures from multi-view images by establishing spatial correspondences. While learning-based methods have significantly advanced the MVS task, challenges such as ambiguous matching caused by textureless surfaces and lighting variations persist. To address these issues, we propose GAP-MVSNet, a framework that leverages surface normals from a monocular normal foundation model as priors to enhance the geometric awareness of reconstruction targets. In this work, surface normal priors are seamlessly integrated into the MVS pipeline to improve depth prediction robustness and accuracy. Specifically, we introduce a structure-aware feature pyramid network that incorporates surface normal information and utilizes uncertainty-aware feature resampling to extract robust image features. Additionally, we present the spatial geometry enhanced regularization that combines sampled depth hypotheses with surface normals to generate a spatial geometric prior, guiding the cost regularization process and enforcing strong spatial coherence, particularly in textureless regions. Furthermore, we design a local consistency depth refinement module that utilizes surface normals to establish depth relationships as a local geometric prior, thereby refining classification-based depth predictions and aligning them with ground truth depth. Extensive experiments on the DTU and Tanks & Temples datasets demonstrate that our method achieves state-of-the-art performance.
关键词	Feature extraction Accuracy Depth measurement Surface treatment Costs Three-dimensional displays Surface reconstruction Surface texture Image reconstruction Pipelines Multi-view stereo deep learning depth estimation 3D reconstruction
DOI	10.1109/TCSVT.2025.3578452
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001631874000050
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://119.78.100.204/handle/2XEOYT63/42978
专题	中国科学院计算技术研究所
通讯作者	Mao, Tianlu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 511442, Peoples R China
推荐引用方式 GB/T 7714	Chen, Kehua,Yuan, Zhenlong,Xiao, Haihong,et al. Learning Multi-View Stereo With Geometry-Aware Prior[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2025,35(12):12396-12409.
APA	Chen, Kehua,Yuan, Zhenlong,Xiao, Haihong,Mao, Tianlu,&Wang, Zhaoqi.(2025).Learning Multi-View Stereo With Geometry-Aware Prior.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,35(12),12396-12409.
MLA	Chen, Kehua,et al."Learning Multi-View Stereo With Geometry-Aware Prior".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 35.12(2025):12396-12409.