Outlier-Robust Diffusion Solvers for Inverse Problems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Yang, Liu, Jiahua, Pang, Tongyao, Li, Wen, Liu, Zhaoqiang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914549353938944
author Zheng, Yang
Liu, Jiahua
Pang, Tongyao
Li, Wen
Liu, Zhaoqiang
author_facet Zheng, Yang
Liu, Jiahua
Pang, Tongyao
Li, Wen
Liu, Zhaoqiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09477
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Outlier-Robust Diffusion Solvers for Inverse Problems
Zheng, Yang
Liu, Jiahua
Pang, Tongyao
Li, Wen
Liu, Zhaoqiang
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Outlier-Robust Diffusion Solvers for Inverse Problems
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.09477