Generative Preprocessing for Image Compression with Pre-trained Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Mengxi, Zhao, Shijie, Li, Junlin, Zhang, Li
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918252072927232
author Guo, Mengxi
Zhao, Shijie
Li, Junlin
Zhang, Li
author_facet Guo, Mengxi
Zhao, Shijie
Li, Junlin
Zhang, Li
contents Preprocessing is a well-established technique for optimizing compression, yet existing methods are predominantly Rate-Distortion (R-D) optimized and constrained by pixel-level fidelity. This work pioneers a shift towards Rate-Perception (R-P) optimization by, for the first time, adapting a large-scale pre-trained diffusion model for compression preprocessing. We propose a two-stage framework: first, we distill the multi-step Stable Diffusion 2.1 into a compact, one-step image-to-image model using Consistent Score Identity Distillation (CiD). Second, we perform a parameter-efficient fine-tuning of the distilled model's attention modules, guided by a Rate-Perception loss and a differentiable codec surrogate. Our method seamlessly integrates with standard codecs without any modification and leverages the model's powerful generative priors to enhance texture and mitigate artifacts. Experiments show substantial R-P gains, achieving up to a 30.13% BD-rate reduction in DISTS on the Kodak dataset and delivering superior subjective visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
Guo, Mengxi
Zhao, Shijie
Li, Junlin
Zhang, Li
Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
Preprocessing is a well-established technique for optimizing compression, yet existing methods are predominantly Rate-Distortion (R-D) optimized and constrained by pixel-level fidelity. This work pioneers a shift towards Rate-Perception (R-P) optimization by, for the first time, adapting a large-scale pre-trained diffusion model for compression preprocessing. We propose a two-stage framework: first, we distill the multi-step Stable Diffusion 2.1 into a compact, one-step image-to-image model using Consistent Score Identity Distillation (CiD). Second, we perform a parameter-efficient fine-tuning of the distilled model's attention modules, guided by a Rate-Perception loss and a differentiable codec surrogate. Our method seamlessly integrates with standard codecs without any modification and leverages the model's powerful generative priors to enhance texture and mitigate artifacts. Experiments show substantial R-P gains, achieving up to a 30.13% BD-rate reduction in DISTS on the Kodak dataset and delivering superior subjective visual quality.
title Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
topic Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2512.15270