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.
@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}
}