让噪声训练的扩散模型生成清晰图像，无需重训。
SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images
- 生成时通过频谱截断与SDEdit重生成高频细节
- 在CIFAR-10和SIDD上显著优于现有方法
- 理论推导频段与初始时间步关系，避免过量加噪
在噪声数据集上训练的扩散模型常复现高频训练伪影，严重降低生成质量。为此，我们提出SCoRe（频谱截断重生成），一种无需训练、仅在生成阶段使用的频谱再生方法，用于从噪声训练的扩散模型中生成清晰图像。利用扩散模型的频谱偏差特性——即从低频线索推断高频细节——SCoRe通过频谱截断抑制生成图像中被污染的高频成分，并借助SDEdit重生成。关键在于，我们基于径向平均功率谱密度（RAPSD）推导出截断频率与SDEdit初始化时间步之间的理论映射，有效防止重生成过程中的过度噪声注入。在合成数据集CIFAR-10和真实世界数据集SIDD上的实验表明，SCoRe显著优于后处理及抗噪基线方法，可在不进行任何重训练或微调的前提下，将生成样本恢复至接近干净图像分布。
原文摘要 · Abstract (English)
Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectral Cutoff Regeneration), a training-free, generation-time spectral regeneration method for clean image generation from diffusion models trained on noisy images. Leveraging the spectral bias of diffusion models, which infer high-frequency details from low-frequency cues, SCoRe suppresses corrupted high-frequency components of a generated image via a frequency cutoff and regenerates them via SDEdit. Crucially, we derive a theoretical mapping between the cutoff frequency and the SDEdit initialization timestep based on Radially Averaged Power Spectral Density (RAPSD), which prevents excessive noise injection during regeneration. Experiments on synthetic (CIFAR-10) and real-world (SIDD) noisy datasets demonstrate that SCoRe substantially outperforms post-processing and noise-robust baselines, restoring samples closer to clean image distributions without any retraining or fine-tuning.
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。