English

CompressAI: a PyTorch library and evaluation platform for end-to-end compression research

Computer Vision and Pattern Recognition 2020-11-06 v1 Image and Video Processing

Abstract

This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs. In particular, CompressAI includes pre-trained models and evaluation tools to compare learned methods with traditional codecs. Multiple models from the state-of-the-art on learned end-to-end compression have thus been reimplemented in PyTorch and trained from scratch. We also report objective comparison results using PSNR and MS-SSIM metrics vs. bit-rate, using the Kodak image dataset as test set. Although this framework currently implements models for still-picture compression, it is intended to be soon extended to the video compression domain.

Keywords

Cite

@article{arxiv.2011.03029,
  title  = {CompressAI: a PyTorch library and evaluation platform for end-to-end compression research},
  author = {Jean Bégaint and Fabien Racapé and Simon Feltman and Akshay Pushparaja},
  journal= {arXiv preprint arXiv:2011.03029},
  year   = {2020}
}

Comments

19 pages, 11 figures

R2 v1 2026-06-23T19:56:49.545Z