Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.01641 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918485540470784 |
|---|---|
| author | Liu, Xiaoyang Zhou, Zhengyan Xu, Zihang Cao, Jiezhang Chen, Zheng Zhang, Yulun |
| author_facet | Liu, Xiaoyang Zhou, Zhengyan Xu, Zihang Cao, Jiezhang Chen, Zheng Zhang, Yulun |
| contents | Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion models, which are rich in real-world modeling, have shown great promise for high-quality image restoration tasks such as deblurring, demonstrating stronger generative capabilities than CNN and transformer-based methods. However, challenges such as unbearable inference time and compromised fidelity still limit the full potential of the diffusion models. To address this, we introduce FideDiff, a novel single-step diffusion model designed for high-fidelity deblurring. We reformulate motion deblurring as a diffusion-like process where each timestep represents a progressively blurred image, and we train a consistency model that aligns all timesteps to the same clean image. By reconstructing training data with matched blur trajectories, the model learns temporal consistency, enabling accurate one-step deblurring. We further enhance model performance by integrating Kernel ControlNet for blur kernel estimation and introducing adaptive timestep prediction. Our model achieves superior performance on full-reference metrics, surpassing previous diffusion-based methods and matching the performance of other state-of-the-art models. FideDiff offers a new direction for applying pre-trained diffusion models to high-fidelity image restoration tasks, establishing a robust baseline for further advancing diffusion models in real-world industrial applications. Our dataset and code will be available at https://github.com/xyLiu339/FideDiff. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01641 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring Liu, Xiaoyang Zhou, Zhengyan Xu, Zihang Cao, Jiezhang Chen, Zheng Zhang, Yulun Computer Vision and Pattern Recognition Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion models, which are rich in real-world modeling, have shown great promise for high-quality image restoration tasks such as deblurring, demonstrating stronger generative capabilities than CNN and transformer-based methods. However, challenges such as unbearable inference time and compromised fidelity still limit the full potential of the diffusion models. To address this, we introduce FideDiff, a novel single-step diffusion model designed for high-fidelity deblurring. We reformulate motion deblurring as a diffusion-like process where each timestep represents a progressively blurred image, and we train a consistency model that aligns all timesteps to the same clean image. By reconstructing training data with matched blur trajectories, the model learns temporal consistency, enabling accurate one-step deblurring. We further enhance model performance by integrating Kernel ControlNet for blur kernel estimation and introducing adaptive timestep prediction. Our model achieves superior performance on full-reference metrics, surpassing previous diffusion-based methods and matching the performance of other state-of-the-art models. FideDiff offers a new direction for applying pre-trained diffusion models to high-fidelity image restoration tasks, establishing a robust baseline for further advancing diffusion models in real-world industrial applications. Our dataset and code will be available at https://github.com/xyLiu339/FideDiff. |
| title | FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.01641 |