用预训练扩散模型做图像压缩前处理，提升画质同时大幅降低码率。
Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
- 用一致性分数蒸馏将扩散模型压缩为单步图像生成器。
- 在Kodak数据集上实现30.13%的BD-rate降低，主观画质更优。
- 无需修改现有编码器，适合追求高质量低码率的图像压缩场景。
预处理是优化图像压缩的有效手段，但现有方法主要基于率失真（R-D）准则，受限于像素级保真度。本文首次提出转向率感知（R-P）优化，利用大规模预训练扩散模型进行压缩前处理。提出两阶段框架：首先通过一致分数身份蒸馏（CiD）将多步Stable Diffusion 2.1压缩为轻量单步图像到图像模型；其次，在可参数高效微调的注意力模块上，以率感知损失和可微编码器代理为指导进行优化。该方法无缝集成于标准编码器，无需修改，利用模型强大的生成先验增强纹理并抑制伪影。实验显示显著的R-P性能提升，在Kodak数据集上DISTS指标下实现最高30.13%的BD-rate降低，并获得更优主观视觉质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。