Fast Training-free Perceptual Image Compression

TL;DR

This paper introduces a training-free, fast perceptual image compression method that enhances existing codecs' quality with theoretical guarantees, significantly reducing decoding time while maintaining or improving perceptual quality.

Contribution

It proposes a novel training-free algorithm that improves perceptual quality of existing codecs with guaranteed theoretical performance, applicable to non-differentiable codecs and various decoding time budgets.

Findings

Reduces decoding time from 1 minute to 0.1-10 seconds.

Achieves comparable FID to previous codecs with faster decoding.

Outperforms previous conditional generative codecs in perceptual quality.

Abstract

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 $\approx 0.1$s, $0.1-10$s and $\ge 10$s. Our approach: 1). improves the decoding time of training-free codec from 1 min to $0.1-10$s 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.