Single-step Diffusion for Image Compression at Ultra-Low Bitrates

TL;DR

This paper introduces a single-step diffusion model for ultra-low bitrate image compression that achieves high perceptual quality and significantly faster decoding, making generative codecs more practical.

Contribution

The paper presents a novel single-step diffusion approach with VQ-Residual training and rate-aware noise modulation for efficient, high-quality image compression at ultra-low bitrates.

Findings

Decodes images 50x faster than previous diffusion methods.

Maintains competitive compression performance with state-of-the-art techniques.

Enhances perceptual quality at extremely low bitrates.

Abstract

Although there have been significant advancements in image compression techniques, such as standard and learned codecs, these methods still suffer from severe quality degradation at extremely low bits per pixel. While recent diffusion-based models provided enhanced generative performance at low bitrates, they often yields limited perceptual quality and prohibitive decoding latency due to multiple denoising steps. In this paper, we propose the single-step diffusion model for image compression that delivers high perceptual quality and fast decoding at ultra-low bitrates. Our approach incorporates two key innovations: (i) Vector-Quantized Residual (VQ-Residual) training, which factorizes a structural base code and a learned residual in latent space, capturing both global geometry and high-frequency details; and (ii) rate-aware noise modulation, which tunes denoising strength to match the desired bitrate. Extensive experiments show that ours achieves comparable compression performance to state-of-the-art methods while improving decoding speed by about 50x compared to prior diffusion-based methods, greatly enhancing the practicality of generative codecs.