面向逆问题的离群点鲁棒扩散求解器
Outlier-Robust Diffusion Solvers for Inverse Problems
把 Huber 型迭代重加权最小二乘与共轭梯度求解嵌入扩散逆问题采样，为测量含离群点（如去噪、超分、修复中的坏像素/遮挡）时提供可直接替换的鲁棒求解器。
原文依据 we formulate an iteratively reweighted least squares objective based on the Huber loss to address the outliers
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于扩散模型（DM）求解逆问题（IP）的方法近来取得了显著性能。然而，基于 DM 的方法通常难以应对真实测量中常见的离群点。在本工作中，为处理含离群点的逆问题，我们首先通过显式噪声估计对测量进行修正，以减轻噪声的影响。随后，我们基于 Huber 损失构建迭代重加权最小二乘目标，以应对离群点。我们提出一种利用梯度下降近似求解该鲁棒目标对应优化问题的方法。为避免梯度下降方法所需的精细学习率调参，我们进一步采用共轭梯度法并配合一种高效的更新策略。在多个图像数据集上针对线性与非线性任务、在多种条件下开展的大量实验表明，我们提出的方法对离群点具有鲁棒性，并在多数情况下优于近期的基于 DM 的方法。
英文原文摘要 1032 字符
Methods based on diffusion models (DMs) for solving inverse problems (IPs) have recently achieved remarkable performance. However, DM-based methods typically struggle against outliers, which are common in real-world measurements. In this work, to tackle IPs with outliers, we first refine the measurement via explicit noise estimation to mitigate the effect of noise. Subsequently, we formulate an iteratively reweighted least squares objective based on the Huber loss to address the outliers. We propose a method utilizing gradient descent to approximately solve the corresponding optimization problem for the robust objective. To avoid delicate tuning of the learning rate required by the gradient descent method, we further employ the conjugate gradient method with an efficient strategy for updating. Extensive experiments on multiple image datasets for linear and nonlinear tasks under various conditions demonstrate that our proposed methods exhibit robustness to outliers and outperform recent DM-based methods in most cases.