DeCo：面向端到端图像生成的频率解耦像素扩散
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
把高频细节交给轻量像素解码器、让 DiT 专注低频语义的频率解耦思路，可直接迁移到任何在像素空间做扩散/流匹配的生成框架，用来降低训练与采样成本；配套的频率感知流匹配损失也可复用于其他扩散模型的损失设计。
原文依据 we leverage a lightweight pixel decoder to generate high-frequency details conditioned on semantic guidance from the DiT
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论像素扩散旨在以端到端方式直接在像素空间中生成图像。该方法规避了潜空间扩散中变分自编码器的局限，具备更高的模型容量。现有像素扩散模型训练与推理缓慢，因为它们通常在单个扩散 Transformer（DiT）中同时建模高频信号与低频语义。为追求更高效的像素扩散范式，我们提出频率解耦的像素扩散框架 DeCo。基于将高频与低频成分的生成解耦这一直觉，我们利用一个轻量级像素解码器，以 DiT 提供的语义引导为条件生成高频细节。由此 DiT 得以专注于建模低频语义。此外，我们引入频率感知的流匹配损失，对视觉上显著的频率予以强调，同时抑制不显著的频率。大量实验表明，DeCo 在像素扩散模型中取得领先性能，在 ImageNet 上达到弗雷歇初始距离 1.62（256x256）与 2.22（512x512），缩小了与潜空间扩散方法的差距。此外，我们预训练的文本到图像模型在系统级比较中于 GenEval 上取得 0.86 的领先综合得分。
英文原文摘要 1286 字符
Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer from slow training and inference, as they usually model both high-frequency signals and low-frequency semantics within a single diffusion transformer (DiT). To pursue a more efficient pixel diffusion paradigm, we propose the frequency-**DeCo**upled pixel diffusion framework. With the intuition to decouple the generation of high and low frequency components, we leverage a lightweight pixel decoder to generate high-frequency details conditioned on semantic guidance from the DiT. This thus frees the DiT to specialize in modeling low-frequency semantics. In addition, we introduce a frequency-aware flow-matching loss that emphasizes visually salient frequencies while suppressing insignificant ones. Extensive experiments show that DeCo achieves superior performance among pixel diffusion models, attaining FID of **1.62** (256x256) and **2.22** (512x512) on ImageNet, closing the gap with latent diffusion methods. Furthermore, our pretrained text-to-image model achieves a leading overall score of 0.86 on GenEval in system-level comparison.