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

2025-08-06

AI Summary

To address the high decoding latency and low fidelity bottlenecks in diffusion-based image compression, this paper proposes SODEC, a single-step diffusion image compression model. Methodologically, SODEC innovatively integrates the high-informativeness latent space of a pretrained VAE into a single-step diffusion framework—eliminating iterative sampling—and introduces a fidelity-guidance module that explicitly enforces signal fidelity during reconstruction. Furthermore, it adopts a rate-annealing training strategy to jointly optimize rate-distortion performance and perceptual quality. Experimental results demonstrate that SODEC achieves state-of-the-art performance across multiple benchmarks: it reduces decoding latency by over 20× compared to multi-step diffusion methods and attains superior rate-distortion–perception trade-offs, particularly at low bitrates.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

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$ imes$. Code is released at: https://github.com/zhengchen1999/SODEC.

Problem

• Reduce decoding latency in diffusion-based image compression
• Improve fidelity by reducing reliance on generative priors
• Enhance performance at extremely low bitrates

Innovation

• Single-step decoding replaces multi-step denoising
• Fidelity guidance module enhances image accuracy
• Rate annealing strategy for low bitrate training