Abstract
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.
Abstract (translated)
预处理是一种已确立的技术，用于优化压缩效果。然而，现有的方法大多以率失真（R-D）为目标，并受限于像素级保真度的要求。本文首次将大规模预训练的扩散模型应用于压缩预处理中，标志着向率感知（R-P）优化的重大转变。我们提出了一种两阶段框架：首先，通过一致分数身份蒸馏（CiD），我们将多步骤的Stable Diffusion 2.1转化为一个紧凑的一步式图像到图像模型。其次，我们在注意力模块上进行参数高效的微调，并利用率感知损失和可微分编解码器代理来指导这一过程。我们的方法可以无缝地与标准编解码器结合使用，无需任何修改，并且能够利用模型的强大生成先验知识来增强纹理并减轻伪影。实验结果表明，在Kodak数据集上，我们的方法在DISTS指标上的BD率（Bitrate-Distortion）减少了高达30.13%，并且提供了更好的主观视觉质量。
URL
https://arxiv.org/abs/2512.15270
