• MindSpore reproduction of HESIC
• • Our contributions
  • Files
  • Environment
  • Command
  • Reproduction results:
  • Cite from:
  • Contributors:

MindSpore reproduction of HESIC

original paper link

Paper Citation:
@inproceedings{deng2021deep,
title={Deep Homography for Efficient Stereo Image Compression},
author={Deng, Xin and Yang, Wenzhe and Yang, Ren and Xu, Mai and Liu, Enpeng and Feng, Qianhan and Timofte, Radu},
booktitle={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages={1492--1501},
year={2021},
organization={IEEE}
}

Our contributions

1. transplant from Pytorch to mindspore (including test scripts and pretrained models).
2. benchmark tests on the origin datasets.
3. compare performance between different frameworks.

Files

to be updated

Environment

to be updated

Command

to be updated

Reproduction results:

to be updated

Cite from:

The project architecture is inherited by https://github.com/ywz978020607/HESIC, and part of the MindSpore code about the HESIC model is referenced by https://github.com/ywz978020607/2021Summer-Image-Compression.

Contributors:

name: Huiming Zheng (the School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University (PKU), Shenzhen, China)
email: hmzheng@stu.pku.edu.cn

If any problems about the project, please contact me with my email.