DeepMVS: Learning Multi-View Stereopsis

Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, Jia-Bin Huang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 2821-2830

Abstract


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.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Huang_2018_CVPR,
author = {Huang, Po-Han and Matzen, Kevin and Kopf, Johannes and Ahuja, Narendra and Huang, Jia-Bin},
title = {DeepMVS: Learning Multi-View Stereopsis},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}