Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.03355 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918137007439872 |
|---|---|
| author | Lin, Qinwei Sun, Xiaopeng Gao, Yu Zhong, Yujie Li, Dengjie Zhao, Zheng Wang, Haoqian |
| author_facet | Lin, Qinwei Sun, Xiaopeng Gao, Yu Zhong, Yujie Li, Dengjie Zhao, Zheng Wang, Haoqian |
| contents | Diffusion models have recently achieved outstanding results in the field of image super-resolution. These methods typically inject low-resolution (LR) images via ControlNet.In this paper, we first explore the temporal dynamics of information infusion through ControlNet, revealing that the input from LR images predominantly influences the initial stages of the denoising process. Leveraging this insight, we introduce a novel timestep-aware diffusion model that adaptively integrates features from both ControlNet and the pre-trained Stable Diffusion (SD). Our method enhances the transmission of LR information in the early stages of diffusion to guarantee image fidelity and stimulates the generation ability of the SD model itself more in the later stages to enhance the detail of generated images. To train this method, we propose a timestep-aware training strategy that adopts distinct losses at varying timesteps and acts on disparate modules. Experiments on benchmark datasets demonstrate the effectiveness of our method. Code: https://github.com/SleepyLin/TASR |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03355 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TASR: Timestep-Aware Diffusion Model for Image Super-Resolution Lin, Qinwei Sun, Xiaopeng Gao, Yu Zhong, Yujie Li, Dengjie Zhao, Zheng Wang, Haoqian Computer Vision and Pattern Recognition Diffusion models have recently achieved outstanding results in the field of image super-resolution. These methods typically inject low-resolution (LR) images via ControlNet.In this paper, we first explore the temporal dynamics of information infusion through ControlNet, revealing that the input from LR images predominantly influences the initial stages of the denoising process. Leveraging this insight, we introduce a novel timestep-aware diffusion model that adaptively integrates features from both ControlNet and the pre-trained Stable Diffusion (SD). Our method enhances the transmission of LR information in the early stages of diffusion to guarantee image fidelity and stimulates the generation ability of the SD model itself more in the later stages to enhance the detail of generated images. To train this method, we propose a timestep-aware training strategy that adopts distinct losses at varying timesteps and acts on disparate modules. Experiments on benchmark datasets demonstrate the effectiveness of our method. Code: https://github.com/SleepyLin/TASR |
| title | TASR: Timestep-Aware Diffusion Model for Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03355 |