{"ID":2861277,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01641","arxiv_id":"2510.01641","title":"FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring","abstract":"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.","short_abstract":"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 capabi...","url_abs":"https://arxiv.org/abs/2510.01641","url_pdf":"https://arxiv.org/pdf/2510.01641v3","authors":"[\"Xiaoyang Liu\",\"Zhengyan Zhou\",\"Zihang Xu\",\"Jiezhang Cao\",\"Zheng Chen\",\"Yulun Zhang\"]","published":"2025-10-02T03:44:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\",\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":608804,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2861277,"paper_url":"https://arxiv.org/abs/2510.01641","paper_title":"FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring","repo_url":"https://github.com/xyLiu339/FideDiff","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}