RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
This addresses the challenge of 3D reconstruction from multi-view images for computer vision applications, with incremental improvements over existing unsupervised methods.
They tackled the problem of inaccurate correspondences in unsupervised Multi-View Stereo due to non-Lambertian surfaces and occlusions, achieving state-of-the-art performance on DTU and Tanks&Temples benchmarks and competitive results compared to supervised methods.
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