用视频扩散模型解决复杂运动模糊，无需估计模糊核。
Image Motion Blur Removal in the Temporal Dimension with Video Diffusion Models
- 将运动模糊视为时间平均现象，用预训练视频扩散模型捕捉动态
- 在合成与真实数据上均优于现有方法，处理复杂模糊更有效
- 适合需要高质量单图去模糊的视觉任务，如摄影修复
多数运动去模糊算法依赖空间域卷积模型，难以应对由相机抖动和物体运动引起的复杂非线性模糊。本文提出一种新型单图像去模糊方法，将运动模糊视为时间维度上的平均现象。核心创新在于利用预训练的视频扩散变换器模型，在隐空间中捕捉多样的运动动态，避免显式模糊核估计，有效适应各类运动模式。算法基于扩散逆问题框架实现。在合成与真实世界数据集上的实验表明，该方法在复杂运动模糊场景下显著优于现有技术。本工作为利用强大视频扩散模型解决单图像去模糊挑战提供了新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。