One-Step Diffusion for Perceptual Image Compression

TL;DR

This paper introduces a one-step diffusion-based image compression method that achieves high perceptual quality with significantly faster inference, making diffusion-based compression more practical for real-world applications.

Contribution

We propose a novel single-step diffusion approach for image compression that reduces inference time and incorporates a feature-based discriminator to improve perceptual quality.

Findings

Achieves comparable compression performance to existing methods.

Provides 46 times faster inference speed.

Uses a discriminator on feature representations for better quality.

Abstract

Diffusion-based image compression methods have achieved notable progress, delivering high perceptual quality at low bitrates. However, their practical deployment is hindered by significant inference latency and heavy computational overhead, primarily due to the large number of denoising steps required during decoding. To address this problem, we propose a diffusion-based image compression method that requires only a single-step diffusion process, significantly improving inference speed. To enhance the perceptual quality of reconstructed images, we introduce a discriminator that operates on compact feature representations instead of raw pixels, leveraging the fact that features better capture high-level texture and structural details. Experimental results show that our method delivers comparable compression performance while offering a 46$\times$ faster inference speed compared to recent diffusion-based approaches. The source code and models are available at https://github.com/cheesejiang/OSDiff.