电子学报2023，Vol.51Issue(11)：3079-3091,13.DOI:10.12263/DZXB.20230353
基于自适应空间稀疏化的高效多视图立体匹配
Adaptive Spatial Sparsification for Efficient Multi-View Stereo Matching
摘要
Abstract
To reduce the high computational complexity in constructing and aggregating cost volumes for multi-view stereo matching,existing methods commonly employ cascaded architectures or iterative optimization.However,these ap-proaches still face two main challenges.The cascaded architectures narrow down the depth sampling range during the re-finement stage,which may lead to erroneous estimation of depth discontinuities.While the inference time of iterative opti-mization networks linearly increases with the number of iterations,making it difficult to meet the requirements of real-time systems.To address these challenges,this paper proposes an efficient multi-view stereo matching network via adaptive spa-tial sparsification.We introduce a sparse matching cost volume that sparsely samples within the complete depth range,re-ducing computational complexity while maintaining the network's ability to model depth-discontinuous regions.Mean-while,we propose a sparse iterative optimization method that progressively prunes regions with converged depth values dur-ing iterations using adaptive variational Dropout,resulting in sub-linear growth in inference time with iteration count.Ex-perimental results on the public datasets,DTU and Tanks&Temples,demonstrate that the proposed method achieves 1.2×and 0.35×improvements of inference speed compared to CasMVSNet and PatchmatchNet,respectively.Moreover,it exhib-its excellent performance in point cloud reconstruction,effectively handles details in depth-discontinuous regions,and dem-onstrates outstanding generalization capability.关键词
多视图立体/三维重建/深度估计/稀疏神经网络/循环神经网络/TransformerKey words
multi-view stereo/3D reconstruction/depth estimation/sparse neural networks/recurrent neural net-works/Transformer分类
计算机与自动化引用本文复制引用
周晓清,王翔,郑锦,百晓..基于自适应空间稀疏化的高效多视图立体匹配[J].电子学报,2023,51(11):3079-3091,13.基金项目
国家自然科学基金(No.62276016,No.62372029)National Natural Science Foundation of China(No.62276016,No.62372029) （No.62276016,No.62372029）
