Abstract
Deep learning has shown to be effective for depth inference in multi-view stereo (MVS). However, the scalability and accuracy still remain an open problem in this domain. This can be attributed to the memory-consuming cost volume representation and inappropriate depth inference. Inspired by the group-wise correlation in stereo matching, we propose an average group-wise correlation similarity measure to construct a lightweight cost volume. This can not only reduce the memory consumption but also reduce the computational burden in the cost volume filtering. Based on our effective cost volume representation, we propose a cascade 3D U-Net module to regularize the cost volume to further boost the performance. Unlike the previous methods that treat multi-view depth inference as a depth regression problem or an inverse depth classification problem, we recast multi-view depth inference as an inverse depth regression task. This allows our network to achieve sub-pixel estimation and be applicable to large-scale scenes. Through extensive experiments on DTU dataset and Tanks and Temples dataset, we show that our proposed network with Correlation cost volume and Inverse DEpth Regression (CIDER1), achieves state-of-the-art results, demonstrating its superior performance on scalability and accuracy.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
54 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Multi-View Stereo Network Based on Attention Mechanism and Neural Volume Rendering;Electronics;2023-11-10
2. Semi-supervised Deep Multi-view Stereo;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
3. Global Balanced Networks for Multi-View Stereo;2023 IEEE International Conference on Image Processing (ICIP);2023-10-08
4. Multi-View Stereo with Learnable Cost Metric;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01
5. Focusing on Cross Views Improves Reconstruction in Unsupervised Multi-View Stereo;2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA);2023-08-18