TDiff: Thermal Plug-And-Play Prior with Patch-Based Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909830881476608 |
|---|---|
| author | Dashpute, Piyush Nezakati, Niki Heidrich, Wolfgang Saragadam, Vishwanath |
| author_facet | Dashpute, Piyush Nezakati, Niki Heidrich, Wolfgang Saragadam, Vishwanath |
| contents | Thermal images from low-cost cameras often suffer from low resolution, fixed pattern noise, and other localized degradations. Available datasets for thermal imaging are also limited in both size and diversity. To address these challenges, we propose a patch-based diffusion framework (TDiff) that leverages the local nature of these distortions by training on small thermal patches. In this approach, full-resolution images are restored by denoising overlapping patches and blending them using smooth spatial windowing. To our knowledge, this is the first patch-based diffusion framework that models a learned prior for thermal image restoration across multiple tasks. Experiments on denoising, super-resolution, and deblurring demonstrate strong results on both simulated and real thermal data, establishing our method as a unified restoration pipeline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06460 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TDiff: Thermal Plug-And-Play Prior with Patch-Based Diffusion Dashpute, Piyush Nezakati, Niki Heidrich, Wolfgang Saragadam, Vishwanath Computer Vision and Pattern Recognition Thermal images from low-cost cameras often suffer from low resolution, fixed pattern noise, and other localized degradations. Available datasets for thermal imaging are also limited in both size and diversity. To address these challenges, we propose a patch-based diffusion framework (TDiff) that leverages the local nature of these distortions by training on small thermal patches. In this approach, full-resolution images are restored by denoising overlapping patches and blending them using smooth spatial windowing. To our knowledge, this is the first patch-based diffusion framework that models a learned prior for thermal image restoration across multiple tasks. Experiments on denoising, super-resolution, and deblurring demonstrate strong results on both simulated and real thermal data, establishing our method as a unified restoration pipeline. |
| title | TDiff: Thermal Plug-And-Play Prior with Patch-Based Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.06460 |