Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression

TL;DR

This paper introduces a plug-and-play latent diffusion module at the decoder to flexibly balance distortion and perceptual quality in neural image compression, significantly improving existing codecs without retraining.

Contribution

It proposes a novel, adjustable diffusion-based feature transformation method that enhances perceptual quality or fidelity in neural image codecs during inference.

Findings

Over 150% LPIPS-BDRate improvement

Maintains original compression performance

Enables flexible distortion-perception tradeoff

Abstract

Neural image compression often faces a challenging trade-off among rate, distortion and perception. While most existing methods typically focus on either achieving high pixel-level fidelity or optimizing for perceptual metrics, we propose a novel approach that simultaneously addresses both aspects for a fixed neural image codec. Specifically, we introduce a plug-and-play module at the decoder side that leverages a latent diffusion process to transform the decoded features, enhancing either low distortion or high perceptual quality without altering the original image compression codec. Our approach facilitates fusion of original and transformed features without additional training, enabling users to flexibly adjust the balance between distortion and perception during inference. Extensive experimental results demonstrate that our method significantly enhances the pretrained codecs with a wide, adjustable distortion-perception range while maintaining their original compression capabilities. For instance, we can achieve more than 150% improvement in LPIPS-BDRate without sacrificing more than 1 dB in PSNR.