Year: 2025
Type: conference-paper
Abstract: Most motion deblurring algorithms rely on spatial-domain convolution models, which struggle with the complex, nonlinear 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.
Authors: Wang Pang, Zhihao Zhan, Xiang Zhu, Yechao Bai
Institution: Nanjing University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4413277683