Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914600798126080 |
|---|---|
| author | Farahbakhsh, Mahdi Kunde, Vishnu Teja Kalathil, Dileep Narayanan, Krishna Chamberland, Jean-Francois |
| author_facet | Farahbakhsh, Mahdi Kunde, Vishnu Teja Kalathil, Dileep Narayanan, Krishna Chamberland, Jean-Francois |
| contents | 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{https://github.com/mahdi-farahbakhsh/DISS}{repository}\footnote{https://github.com/mahdi-farahbakhsh/DISS}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03352 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction Farahbakhsh, Mahdi Kunde, Vishnu Teja Kalathil, Dileep Narayanan, Krishna Chamberland, Jean-Francois Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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{https://github.com/mahdi-farahbakhsh/DISS}{repository}\footnote{https://github.com/mahdi-farahbakhsh/DISS}. |
| title | Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.03352 |