用于图像复原的残差扩散桥模型
Residual Diffusion Bridge Model for Image Restoration
把扩散桥的SDE前向/反向过程写成解析形式，并用残差调制噪声注入与去除，使退化区域被复原、未退化区域不被破坏——这套「按残差自适应加噪」的机制可直接迁移到去噪、去雨、超分等任意配对复原任务，也给出了现有桥模型的统一数学框架。
原文依据 we leverage the residuals from given distributions to modulate the noise injection and removal, enabling adaptive restoration of degraded regions while preserving intact others
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散桥模型在任意成对分布之间建立概率路径，在通用图像复原中展现出巨大潜力。现有方法大多仅将其视为随机插值的简单变体，缺乏统一的分析视角。此外，它们通过全局加噪与去噪不加区分地重建图像，由于重建不完美，不可避免地会扭曲未退化区域。为解决这些挑战，我们提出残差扩散桥模型（RDBM）。具体而言，我们从理论上重新表述了广义扩散桥的随机微分方程，并推导出其前向与反向过程的解析公式。关键在于，我们利用给定分布的残差来调制噪声的注入与去除，从而在自适应复原退化区域的同时保持其他区域完好。此外，我们揭示了现有桥模型的基本数学本质：它们均为 RDBM 的特例，并从经验上验证了所提模型的最优性。大量实验表明，我们的方法在多种图像复原任务上定性与定量均达到最优性能。代码已公开于 https://github.com/MiliLab/RDBM。
英文原文摘要 1347 字符
Diffusion bridge models establish probabilistic paths between arbitrary paired distributions and exhibit great potential for universal image restoration. Most existing methods merely treat them as simple variants of stochastic interpolants, lacking a unified analytical perspective. Besides, they indiscriminately reconstruct images through global noise injection and removal, inevitably distorting undegraded regions due to imperfect reconstruction. To address these challenges, we propose the R esidual D iffusion B ridge M odel (RDBM). Specifically, we theoretically reformulate the stochastic differential equations of generalized diffusion bridge and derive the analytical formulas of its forward and reverse processes. Crucially, we leverage the residuals from given distributions to modulate the noise injection and removal, enabling adaptive restoration of degraded regions while preserving intact others. Additionally, we unravel the fundamental mathematical essence of existing bridge models, all of which are special cases of RDBM and empirically demonstrate the optimality of our proposed models. Extensive experiments are conducted to demonstrate the state-of-the-art performance of our method both qualitatively and quantitatively across diverse image restoration tasks. Code is publicly available at https://github.com/MiliLab/RDBM.