Uploaded September 2022 | Updated November 2026, 3 hours ago
Project: boese0601.github.io/rc-mvsnet
Code: github.com/Boese0601/RC-MVSNet
Paper: arxiv.org/abs/2203.03949
Abstract: Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However, multi-view images in real scenarios observe non-Lambertian surfaces and experience occlusions. In this work, we propose a novel approach with neural rendering (RC-MVSNet) to solve such ambiguity issues of correspondences among views. Specifically, we impose a depth rendering consistency loss to constrain the geometry features close to the object surface to alleviate occlusions. Concurrently, we introduce a reference view synthesis loss to generate consistent supervision, even for non-Lambertian surfaces. Extensive experiments on DTU and Tanks&Temples benchmarks demonstrate that our approach achieves state-of-the-art performance over unsupervised MVS frameworks and competitive performance to many supervised methods. Our code will be released at RC-MVSNet.
Project: boese0601.github.io/rc-mvsnet
Code: github.com/Boese0601/RC-MVSNet
Paper: arxiv.org/abs/2203.03949
Abstract: Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However, multi-view images in real scenarios observe non-Lambertian surfaces and experience occlusions. In this work, we propose a novel approach with neural rendering (RC-MVSNet) to solve such ambiguity issues of correspondences among views. Specifically, we impose a depth rendering consistency loss to constrain the geometry features close to the object surface to alleviate occlusions. Concurrently, we introduce a reference view synthesis loss to generate consistent supervision, even for non-Lambertian surfaces. Extensive experiments on DTU and Tanks&Temples benchmarks demonstrate that our approach achieves state-of-the-art performance over unsupervised MVS frameworks and competitive performance to many supervised methods. Our code will be released at RC-MVSNet.










