We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set of plane-sweep volumes and use the proposed DeepMVS network to predict high-quality disparity maps. The key contributions that enable these results are (1) supervised pretraining on a photorealistic synthetic dataset, (2) an effective method for aggregating information across a set of unordered images, and (3) integrating multi-layer feature activations from the pre-trained VGG-19 network. We validate the efficacy of DeepMVS using the ETH3D Benchmark. Our results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures.
@article{arxiv.1804.00650,
title = {DeepMVS: Learning Multi-view Stereopsis},
author = {Po-Han Huang and Kevin Matzen and Johannes Kopf and Narendra Ahuja and Jia-Bin Huang},
journal= {arXiv preprint arXiv:1804.00650},
year = {2018}
}