Training-free perceptual image codec adopt pre-trained unconditional generative model during decoding to avoid training new conditional generative model. However, they heavily rely on diffusion inversion or sample communication, which take 1 min to intractable amount of time to decode a single image. In this paper, we propose a training-free algorithm that improves the perceptual quality of any existing codec with theoretical guarantee. We further propose different implementations for optimal perceptual quality when decoding time budget is ≈0.1s, 0.1−10s and ≥10s. Our approach: 1). improves the decoding time of training-free codec from 1 min to 0.1−10s with comparable perceptual quality. 2). can be applied to non-differentiable codec such as VTM. 3). can be used to improve previous perceptual codecs, such as MS-ILLM. 4). can easily achieve perception-distortion trade-off. Empirically, we show that our approach successfully improves the perceptual quality of ELIC, VTM and MS-ILLM with fast decoding. Our approach achieves comparable FID to previous training-free codec with significantly less decoding time. And our approach still outperforms previous conditional generative model based codecs such as HiFiC and MS-ILLM in terms of FID. The source code is provided in the supplementary material.
@article{arxiv.2506.16102,
title = {Fast Training-free Perceptual Image Compression},
author = {Ziran Zhu and Tongda Xu and Minye Huang and Dailan He and Xingtong Ge and Xinjie Zhang and Ling Li and Yan Wang},
journal= {arXiv preprint arXiv:2506.16102},
year = {2025}
}