Idempotence is the stability of image codec to re-compression. At the first glance, it is unrelated to perceptual image compression. However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec. Based on this newfound equivalence, we propose a new paradigm of perceptual image codec by inverting unconditional generative model with idempotence constraints. Our codec is theoretically equivalent to conditional generative codec, and it does not require training new models. Instead, it only requires a pre-trained mean-square-error codec and unconditional generative model. Empirically, we show that our proposed approach outperforms state-of-the-art methods such as HiFiC and ILLM, in terms of Fr\'echet Inception Distance (FID). The source code is provided in https://github.com/tongdaxu/Idempotence-and-Perceptual-Image-Compression.
@article{arxiv.2401.08920,
title = {Idempotence and Perceptual Image Compression},
author = {Tongda Xu and Ziran Zhu and Dailan He and Yanghao Li and Lina Guo and Yuanyuan Wang and Zhe Wang and Hongwei Qin and Yan Wang and Jingjing Liu and Ya-Qin Zhang},
journal= {arXiv preprint arXiv:2401.08920},
year = {2025}
}