CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916306824986624 |
|---|---|
| author | Liu, Qingguo Zhuang, Chenyi Gao, Pan Qin, Jie |
| author_facet | Liu, Qingguo Zhuang, Chenyi Gao, Pan Qin, Jie |
| contents | Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details. In this paper, we propose a novel BSR approach, Content-aware Degradation-driven Transformer (CDFormer), to capture both degradation and content representations. However, low-resolution images cannot provide enough content details, and thus we introduce a diffusion-based module $CDFormer_{diff}$ to first learn Content Degradation Prior (CDP) in both low- and high-resolution images, and then approximate the real distribution given only low-resolution information. Moreover, we apply an adaptive SR network $CDFormer_{SR}$ that effectively utilizes CDP to refine features. Compared to previous diffusion-based SR methods, we treat the diffusion model as an estimator that can overcome the limitations of expensive sampling time and excessive diversity. Experiments show that CDFormer can outperform existing methods, establishing a new state-of-the-art performance on various benchmarks under blind settings. Codes and models will be available at \href{https://github.com/I2-Multimedia-Lab/CDFormer}{https://github.com/I2-Multimedia-Lab/CDFormer}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution Liu, Qingguo Zhuang, Chenyi Gao, Pan Qin, Jie Computer Vision and Pattern Recognition Image and Video Processing Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details. In this paper, we propose a novel BSR approach, Content-aware Degradation-driven Transformer (CDFormer), to capture both degradation and content representations. However, low-resolution images cannot provide enough content details, and thus we introduce a diffusion-based module $CDFormer_{diff}$ to first learn Content Degradation Prior (CDP) in both low- and high-resolution images, and then approximate the real distribution given only low-resolution information. Moreover, we apply an adaptive SR network $CDFormer_{SR}$ that effectively utilizes CDP to refine features. Compared to previous diffusion-based SR methods, we treat the diffusion model as an estimator that can overcome the limitations of expensive sampling time and excessive diversity. Experiments show that CDFormer can outperform existing methods, establishing a new state-of-the-art performance on various benchmarks under blind settings. Codes and models will be available at \href{https://github.com/I2-Multimedia-Lab/CDFormer}{https://github.com/I2-Multimedia-Lab/CDFormer}. |
| title | CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2405.07648 |