Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
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_ | 1866918143636537344 |
|---|---|
| author | Wang, Hongjun Chen, Jiyuan Yin, Zhengwei Song, Xuan Zheng, Yinqiang |
| author_facet | Wang, Hongjun Chen, Jiyuan Yin, Zhengwei Song, Xuan Zheng, Yinqiang |
| contents | Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting degradations. Recently, numerous approaches such as Dropout and Feature Alignment have been proposed to suppress models' natural tendency to overfit degradations and yield promising results. Nevertheless, these works have assumed that models overfit to all degradation types (e.g., blur, noise, JPEG), while through careful investigations in this paper, we discover that models predominantly overfit to noise, largely attributable to its distinct degradation pattern compared to other degradation types. In this paper, we propose a targeted feature denoising framework, comprising noise detection and denoising modules. Our approach presents a general solution that can be seamlessly integrated with existing super-resolution models without requiring architectural modifications. Our framework demonstrates superior performance compared to previous regularization-based methods across five traditional benchmarks and datasets, encompassing both synthetic and real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14841 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution Wang, Hongjun Chen, Jiyuan Yin, Zhengwei Song, Xuan Zheng, Yinqiang Computer Vision and Pattern Recognition Artificial Intelligence Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting degradations. Recently, numerous approaches such as Dropout and Feature Alignment have been proposed to suppress models' natural tendency to overfit degradations and yield promising results. Nevertheless, these works have assumed that models overfit to all degradation types (e.g., blur, noise, JPEG), while through careful investigations in this paper, we discover that models predominantly overfit to noise, largely attributable to its distinct degradation pattern compared to other degradation types. In this paper, we propose a targeted feature denoising framework, comprising noise detection and denoising modules. Our approach presents a general solution that can be seamlessly integrated with existing super-resolution models without requiring architectural modifications. Our framework demonstrates superior performance compared to previous regularization-based methods across five traditional benchmarks and datasets, encompassing both synthetic and real-world scenarios. |
| title | Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.14841 |