Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2412.03268 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929615254061056 |
|---|---|
| author | Sun, Xiaopeng Lin, Qinwei Gao, Yu Zhong, Yujie Feng, Chengjian Li, Dengjie Zhao, Zheng Hu, Jie Ma, Lin |
| author_facet | Sun, Xiaopeng Lin, Qinwei Gao, Yu Zhong, Yujie Feng, Chengjian Li, Dengjie Zhao, Zheng Hu, Jie Ma, Lin |
| contents | Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to finetune the existing models can further improve the quality of the generated images. In this paper, we propose a timestep-aware training strategy with reward feedback learning. Specifically, in the initial denoising stages of ISR diffusion, we apply low-frequency constraints to super-resolution (SR) images to maintain structural stability. In the later denoising stages, we use reward feedback learning to improve the perceptual and aesthetic quality of the SR images. In addition, we incorporate Gram-KL regularization to alleviate stylization caused by reward hacking. Our method can be integrated into any diffusion-based ISR model in a plug-and-play manner. Experiments show that ISR diffusion models, when fine-tuned with our method, significantly improve the perceptual and aesthetic quality of SR images, achieving excellent subjective results. Code: https://github.com/sxpro/RFSR |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03268 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RFSR: Improving ISR Diffusion Models via Reward Feedback Learning Sun, Xiaopeng Lin, Qinwei Gao, Yu Zhong, Yujie Feng, Chengjian Li, Dengjie Zhao, Zheng Hu, Jie Ma, Lin Computer Vision and Pattern Recognition Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to finetune the existing models can further improve the quality of the generated images. In this paper, we propose a timestep-aware training strategy with reward feedback learning. Specifically, in the initial denoising stages of ISR diffusion, we apply low-frequency constraints to super-resolution (SR) images to maintain structural stability. In the later denoising stages, we use reward feedback learning to improve the perceptual and aesthetic quality of the SR images. In addition, we incorporate Gram-KL regularization to alleviate stylization caused by reward hacking. Our method can be integrated into any diffusion-based ISR model in a plug-and-play manner. Experiments show that ISR diffusion models, when fine-tuned with our method, significantly improve the perceptual and aesthetic quality of SR images, achieving excellent subjective results. Code: https://github.com/sxpro/RFSR |
| title | RFSR: Improving ISR Diffusion Models via Reward Feedback Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03268 |