analiza aiqbench
This research introduces robust diffusion solvers designed to handle outliers in inverse problems, addressing a key limitation of current diffusion model applications in real-world measurement scenarios. By combining explicit noise estimation with iteratively reweighted least squares and conjugate gradient methods, the approach improves reliability without requiring delicate hyperparameter tuning. The method demonstrates superior performance over existing techniques across various linear and nonlinear image tasks.
Outlier-Robust Diffusion Solvers for Inverse Problems
arXiv:2605.09477v2 Announce Type: replace-cross Abstract: 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. The code is available at https://github.com/StarNextDay/Robust-DAPS.git.
Abstract: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. The code is available at this https URL.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2605.09477 [cs.CV]
(or arXiv:2605.09477v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.09477 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 252 cuvinte
Subiecte conexe
Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors
arXiv · 28 aug. 2026
Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen
arXiv · 25 aug. 2026
Robust Ensemble Guidance for Scientific Inverse Problems
arXiv · 6 oct. 2026
Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance
arXiv · 3 iun. 2026