MVSCRF: Learning Multi-View Stereo With Conditional Random Fields

We present a deep-learning architecture for multi-view stereo with conditional random fields (MVSCRF). Given an arbitrary number of input images, we first use a U-shape neural network to extract deep features incorporating both global and local information, and then build a 3D cost volume for the reference camera. Unlike previous learningbased methods, we explicitly constraint the smoothness of depth maps by using conditional random fields (CRFs) after the stage of cost volume regularization. The CRFs module is implemented as recurrent neural networks so that the whole pipeline can be trained end-to-end. Our results show that the proposed pipeline outperforms previous state-of-the-arts on large-scale DT U dataset. We also achieve comparable results with state-of-the-art learningbased methods on outdoor T anks and T emples dataset without fine-tuning, which demonstrates our method's generalization ability.