Need help with cascade-stereo?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

263 Stars 65 Forks MIT License 14 Commits 13 Opened issues



Services available


Need anything else?

Contributors list

Casacde-Stereo(CVPR2020 Oral)

Official source code of paper Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching, arxiv



  • python 3.6
  • Pytorch == 1.2 (The default interpolation of the high version is different from the low version, which will cause the results to be different)
  • CUDA >= 9.0
pip install -r requirements.txt  --user

Option: Apex

install apex to enable synchronized batch normalization

git clone
cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

CasMVSNet(Multi View Stereo)

Refer to

CasStereoNet(Stereo Matching)

Refer to


If you find this code useful in your research, please cite:

  title={Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching},
  author={Gu, Xiaodong and Fan, Zhiwen and Zhu, Siyu and Dai, Zuozhuo and Tan, Feitong and Tan, Ping},
  journal={arxiv preprint arXiv:1912.06378},


Thanks to Xiaoyang Guo for opening source of his excellent works GwcNet and MVSNet-pytorch. Thanks to Yao Yao for opening source of his excellent work MVSNet.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.