zyangchen / mocha-stereo

[CVPR2024] The official implementation of "MoCha-Stereo: Motif Channel Attention Network for Stereo Matching”.

MoCha-Stereo

[CVPR2024] The official implementation of "MoCha-Stereo: Motif Channel Attention Network for Stereo Matching".

     

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching
Ziyang Chen†, Wei Long†, He Yao†, Yongjun Zhang✱,Bingshu Wang, Yongbin Qin, Jia Wu
CVPR 2024
Correspondence: [email protected]; [email protected]✱
Grateful to Prof. Wenting Li, Prof. Huamin Qu, and anonymous reviewers for their comments on this work.

Demo.mp4

@inproceedings{chen2024mocha,
  title={MoCha-Stereo: Motif Channel Attention Network for Stereo Matching},
  author={Chen, Ziyang and Long, Wei and Yao, He and Zhang, Yongjun and Wang, Bingshu and Qin, Yongbin and Wu, Jia},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={27768--27777},
  year={2024}
}

Todo List

• [CVPR2024] V1 version
  • Paper
  • Code of MoCha-Stereo
• V2 version
  • Preprint manuscript
  • Code of MoCha-V2

MoCha-Stereo will be released in this repository in July, 2024.

For researchers at Guizhou University, I have made the code available in our internal repository. Therefore, you do not need to contact me to get the code, just request access to the repository.

Acknowledgements

• This project borrows the code from IGEV, DLNR, RAFT-Stereo, GwcNet. We thank the original authors for their excellent works!
• Grateful to Prof. Wenting Li, Prof. Huamin Qu, and anonymous reviewers for their comments on this project.
• This project is supported by Science and Technology Planning Project of Guizhou Province, Department of Science and Technology of Guizhou Province, China (Project No. [2023]159).
• This project is supported by Natural Science Research Project of Guizhou Provincial Department of Education, China (QianJiaoJi[2022]029, QianJiaoHeKY[2021]022).

mocha-stereo's Issues

请问大概什么时候会公开源码呢？

请问MCA是如何更关注边缘信息的？

在论文中您写到f_pre = F(f - G(f))， 其中G是高通滤波器，所以应该只有高频信息也就是边缘会通过，那么f-G(f)会将这些边缘信息变成0，而低频信息不变，那么我在求和的时候，高频信息的响应值应该更低才对啊，为什么会更关注重复的几何结构呢？这里不是很理解，麻烦您解答一下，万分感谢！

Correction

There is a writing error in the paper published on cvpr. Please refer to the Arxiv version.

Invite your POSTER for our pre-heat for the CVPR offline conference in Seattle

We sincerely look forward to your poster and will arrange a collection (will show on bilibili)for all authors as a pre-heat for the offline conference. It is convenient for everyone to discuss the posters in advance and this will be a period of significant memory for everyone. You can also send us the exhibition information with poster.

Our email ：[email protected]
WeChat：AIDriver002

where is the papaer?

Hi great works! but Where can I get a download link for this paper?