Most motion deblurring algorithms rely on spatial-domain convolution models, which struggle with the complex, non-linear blur arising from camera shake and object motion. In contrast, we propose a novel single-image deblurring approach that treats motion blur as a temporal averaging phenomenon. Our core innovation lies in leveraging a pre-trained video diffusion transformer model to capture diverse motion dynamics within a latent space. It sidesteps explicit kernel estimation and effectively accommodates diverse motion patterns. We implement the algorithm within a diffusion-based inverse problem framework. Empirical results on synthetic and real-world datasets demonstrate that our method outperforms existing techniques in deblurring complex motion blur scenarios. This work paves the way for utilizing powerful video diffusion models to address single-image deblurring challenges.
@article{arxiv.2501.12604,
title = {Image Motion Blur Removal in the Temporal Dimension with Video Diffusion Models},
author = {Wang Pang and Zhihao Zhan and Xiang Zhu and Yechao Bai},
journal= {arXiv preprint arXiv:2501.12604},
year = {2025}
}