论文标题
RC-MVSNET：无监督的多视图立体声，带有神经渲染
RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
论文作者
论文摘要
在不同观点之间找到准确的对应关系的是无监督的多视图立体声（MV）的跟腱。现有方法是基于相应像素具有相似的光度特征的假设。但是，在实际场景中，多视图图像观察到非斜面表面和经历的遮挡。在这项工作中，我们提出了一种新型的神经渲染方法（RC-MVSNET），以解决观点之间对应关系的歧义问题。具体而言，我们施加了一个深度渲染一致性损失，以限制靠近对象表面的几何特征以减轻遮挡。同时，我们引入了参考视图综合损失，以产生一致的监督，即使是针对非lambertian表面。关于DTU和坦克\＆Semples基准的广泛实验表明，我们的RC-MVSNET方法在无监督的MVS框架上实现了最先进的性能以及许多监督方法的竞争性能。
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
