jiangweibeta / checkerboard-context-model-for-efficient-learned-image-compression

Unofficial pytorch implementation of CVPR2021 paper "Checkerboard Context Model for Efficient Learned Image Compression".

Checkerboard-Context-Model-for-Efficient-Learned-Image-Compression

Update

Cheng2020AnchorwithCheckerboard(cheng2020anchor with checkerboard context module) and CheckerboardContext.py

Environment

Ubuntu 18.04

Python 3.6

Pytorch 1.9.1

CompressAI 1.1.8

Train & Test

You can use example code from CompressAI to train and test a model

Reference

https://interdigitalinc.github.io/CompressAI/

https://arxiv.org/abs/2103.15306v2

Cite

@misc{jiang2021unofficialckbd,
    author={Jiang, Wei},
    title={Unofficial Checkerboard Context Model},
    howpublished={\url{https://github.com/JiangWeibeta/Checkerboard-Context-Model-for-Efficient-Learned-Image-Compression}},
    year={2021}
}

@inproceedings{he2021checkerboard,
  title={Checkerboard context model for efficient learned image compression},
  author={He, Dailan and Zheng, Yaoyan and Sun, Baocheng and Wang, Yan and Qin, Hongwei},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={14771--14780},
  year={2021}
}

checkerboard-context-model-for-efficient-learned-image-compression's Issues

model evaluation results on Kodak

Thanks for your work of the code! I used the [CheckerboardAutogressivev2.py] based on the Minnen2018 in the version2 folder to train a model, but the evaluation results on Kodak dataset is worse than the results given in CompressAI. The PSNR is about 4dB lower than CompressAI‘s while at the same bit rate. Have you evaluate your model on Kodak? Thank you!