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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Park, Chanung, Lee, Joo Chan, Ko, Jong Hwan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914050148925440
author Park, Chanung
Lee, Joo Chan
Ko, Jong Hwan
author_facet Park, Chanung
Lee, Joo Chan
Ko, Jong Hwan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Single-step Diffusion for Image Compression at Ultra-Low Bitrates
Park, Chanung
Lee, Joo Chan
Ko, Jong Hwan
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Single-step Diffusion for Image Compression at Ultra-Low Bitrates
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.16572