Yulun Zhang, Jiezhang Cao, Zheng Chen, Xiaoyang Liu, Zhengyan Zhou, Zihang Xu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 diffusionbased methods and matching the performance of other state-of-the-art models. FideDiff offers a new direction for applying pre-trained diffusion models to highfidelity 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. RealBlur-J (scene204-12) Blurry Restormer HI-Diff UFPNet AdaRevD Zamir et al. (2022) Chen et al. (2023) Fang et al. (2023) Mao et al. (2024)
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2510.01641")
get_code_for_paper("2510.01641")
have("2510.01641")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2510.01641.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2510.01641)
Connect an agent — have() is free.