阐明基于任意噪声的扩散模型的设计空间
Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
将扩散模型的设计空间从固定高斯噪声推广到任意噪声模式，为图像复原任务提供了一种可减少复原距离、且不增加计算开销的通用框架，可直接用于去噪、去伪影等底层视觉问题。
原文依据 EDA expands noise pattern flexibility while preserving EDM's modularity, with rigorous proof that increased noise complexity introduces no additional computational overhead during restoration.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管 EDM 旨在统一扩散模型的设计空间，但其对固定高斯噪声的依赖使其无法解释新兴的、扩散任意噪声的流式方法。此外，我们的研究表明，EDM 强制注入高斯噪声对图像复原任务有不利影响，因为它会破坏退化图像、过度延长复原距离并增加任务复杂度。为了在统一理论框架内解释处理不同噪声模式的多种方法并最小化复原距离，我们提出了 EDA，它阐明了任意噪声扩散模型的设计空间。在理论上，EDA 在保持 EDM 模块化的同时扩展了噪声模式的灵活性，并严格证明了增加噪声复杂度不会在复原过程中引入额外的计算开销。EDA 在三个代表性的医学图像去噪和自然图像复原任务上得到了验证：MRI 偏置场校正（全局平滑噪声）、CT 金属伪影去除（全局锐利噪声）和自然图像阴影去除（局部边界感知噪声）。仅需 5 步采样，在医学和自然任务上就取得了与专用方法相竞争的结果，展示了 EDA 在图像复原方面强大的泛化能力。代码可在 https://github.com/PerceptionComputingLab/EDA 获取。
英文原文摘要 1376 字符
Although EDM aims to unify the design space of diffusion models, its reliance on fixed Gaussian noise prevents it from explaining emerging flow-based methods that diffuse arbitrary noise. Moreover, our study reveals that EDM's forcible injection of Gaussian noise has adverse effects on image restoration task, as it corrupts the degraded images, overextends the restoration distance, and increases the task's complexity. To interpret diverse methods for handling distinct noise patterns within a unified theoretical framework and to minimize the restoration distance, we propose EDA, which Elucidates the Design space of Arbitrary-noise diffusion models. Theoretically, EDA expands noise pattern flexibility while preserving EDM's modularity, with rigorous proof that increased noise complexity introduces no additional computational overhead during restoration. EDA is validated on three representative medical image denoising and natural image restoration tasks: MRI bias field correction (global smooth noise), CT metal artifact removal (global sharp noise) and natural image shadow removal (local boundary-aware noise). With only 5 sampling steps, competitive results against specialized methods across medical and natural tasks demonstrate EDA's strong generalization capability for image restoration. Code is available at: https://github.com/PerceptionComputingLab/EDA.