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 RC-MVSNet approach achieves state-of-the-art performance over unsupervised MVS frameworks and competitive performance to many supervised methods.The code is released at https://github.com/Boese0601/RC-MVSNet
@article{arxiv.2203.03949,
title = {RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering},
author = {Di Chang and Aljaž Božič and Tong Zhang and Qingsong Yan and Yingcong Chen and Sabine Süsstrunk and Matthias Nießner},
journal= {arXiv preprint arXiv:2203.03949},
year = {2022}
}
Comments
Accepted by ECCV 2022, Project Page: https://boese0601.github.io/rc-mvsnet/