English

DeepMVS: Learning Multi-view Stereopsis

Computer Vision and Pattern Recognition 2018-04-03 v1

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.

Keywords

Cite

@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}
}

Comments

CVPR 2018. Project page: https://phuang17.github.io/DeepMVS/ Code: https://github.com/phuang17/DeepMVS

R2 v1 2026-06-23T01:11:52.573Z