DeepMVS: Learning Multi-view Stereopsis

Authors:
  • PHPo-Han Huang
    Po-Han Huang
  • KMKevin Matzen
    Kevin Matzen
  • JKJohannes Kopf
    Johannes Kopf
  • NANarendra Ahuja
    Narendra Ahuja
  • JHJia-Bin Huang
    Jia-Bin Huang

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.

This publication has 28 references indexed in Scilit: