Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Zheng, Zhou, Mingde, Guo, Jinpei, Yuan, Jiale, Ji, Yifei, Zhang, Yulun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918226857820160
author Chen, Zheng
Zhou, Mingde
Guo, Jinpei
Yuan, Jiale
Ji, Yifei
Zhang, Yulun
author_facet Chen, Zheng
Zhou, Mingde
Guo, Jinpei
Yuan, Jiale
Ji, Yifei
Zhang, Yulun
contents Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from over-reliance on generative priors. To address these issues, we propose SODEC, a novel single-step diffusion image compression model. We argue that in image compression, a sufficiently informative latent renders multi-step refinement unnecessary. Based on this insight, we leverage a pre-trained VAE-based model to produce latents with rich information, and replace the iterative denoising process with a single-step decoding. Meanwhile, to improve fidelity, we introduce the fidelity guidance module, encouraging output that is faithful to the original image. Furthermore, we design the rate annealing training strategy to enable effective training under extremely low bitrates. Extensive experiments show that SODEC significantly outperforms existing methods, achieving superior rate-distortion-perception performance. Moreover, compared to previous diffusion-based compression models, SODEC improves decoding speed by more than 20$\times$. Code is released at: https://github.com/zhengchen1999/SODEC.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04979
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression
Chen, Zheng
Zhou, Mingde
Guo, Jinpei
Yuan, Jiale
Ji, Yifei
Zhang, Yulun
Computer Vision and Pattern Recognition
Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from over-reliance on generative priors. To address these issues, we propose SODEC, a novel single-step diffusion image compression model. We argue that in image compression, a sufficiently informative latent renders multi-step refinement unnecessary. Based on this insight, we leverage a pre-trained VAE-based model to produce latents with rich information, and replace the iterative denoising process with a single-step decoding. Meanwhile, to improve fidelity, we introduce the fidelity guidance module, encouraging output that is faithful to the original image. Furthermore, we design the rate annealing training strategy to enable effective training under extremely low bitrates. Extensive experiments show that SODEC significantly outperforms existing methods, achieving superior rate-distortion-perception performance. Moreover, compared to previous diffusion-based compression models, SODEC improves decoding speed by more than 20$\times$. Code is released at: https://github.com/zhengchen1999/SODEC.
title Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.04979