分频处理图像生成，提升像素空间扩散模型的效率与质量
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
- 将图像生成分解为高低频分量，分别设计传输路径
- 在256×256下达到1.91 FID，低NFE阶段表现更优
- 适合追求高效、高质量像素级生成的研究者
像素空间扩散模型因避免了变分自编码器（VAEs）引入的表征瓶颈，重新成为有前景的替代方案。然而，现有方法大多将图像生成视为频率同质过程，忽视了低频与高频成分在角色和学习动态上的差异。为此，我们提出FREPix——一种面向像素空间生成的频率异构流匹配框架。FREPix显式地将生成过程分解为低频与高频成分，为其分配独立的传输路径，使用因子化网络分别预测，并通过频率感知目标进行训练。由此，从粗到细的生成成为明确的设计原则而非隐含行为。在ImageNet类到图像生成任务中，FREPix在像素空间生成模型中表现具有竞争力，在256×256下达到1.91 FID，512×512下为2.38 FID，尤其在训练初期和低NFE（非迭代步数）条件下表现突出。
原文摘要 · Abstract (English)
Pixel-space diffusion has re-emerged as a promising alternative to latent-space generation because it avoids the representation bottleneck introduced by VAEs. Yet most existing methods still treat image generation as a frequency-homogeneous process, overlooking the distinct roles and learning dynamics of low- and high-frequency components. To address this, we propose FREPix, a FREquency-heterogeneous flow matching framework for Pixel-space image generation. FREPix explicitly decomposes generation into low- and high-frequency components, assigns them separate transport paths, predicts them with a factorized network, and trains them with a frequency-aware objective. In this way, coarse-to-fine generation becomes an explicit design principle rather than an implicit behavior. On ImageNet class-to-image generation, FREPix achieves competitive results among pixel-space generation models, reaching 1.91 FID at $256\times256$ and 2.38 FID at $512\times512$, with particularly strong performance in the early stages of training and in the low-NFE regime.
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。