Abstract:Diffusion models have been used as priors for solving inverse problems. However, existing approaches typically overlook side information that could significantly improve reconstruction quality, especially in severely ill-posed settings. In this work, we propose a novel framework that incorporates side information into existing diffusion-based inverse problem solvers via inference-time search, in a plug-and-play, training-free manner. Through extensive experiments across a range of inverse problems, including inpainting, super-resolution, and several deblurring tasks, and across multiple diffusion-based inverse problem solvers (DPS, DAPS, and MPGD), we show that augmenting each solver with our framework consistently improves the quality of the reconstructions over the corresponding original method. To demonstrate the generality of our approach, we consider diverse forms of side information, including reference images, textual descriptions, and anatomical MRI scans. The code is available at this \href{this https URL}{repository}\footnote{this https URL}.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.03352 [cs.CV] |
| (or arXiv:2510.03352v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2510.03352 arXiv-issued DOI via DataCite |
From: Vishnu Teja Kunde [view email]
[v1]
Thu, 2 Oct 2025 20:16:00 UTC (31,971 KB)
[v2]
Tue, 17 Feb 2026 17:13:23 UTC (55,270 KB)
[v3]
Tue, 26 May 2026 02:33:06 UTC (12,832 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。