面向视频修复的流引导扩散
计算机视觉与模式识别
2025-01-24 v2
摘要
视频修复一直受大规模运动与低光照等复杂场景挑战。现有方法（包括新兴扩散模型）在质量与效率上面临局限。本文引入面向视频修复的流引导扩散模型（FGDVI），一种通过复用现成图像生成扩散模型显著增强时间一致性与修复质量的新途径。我们采用光流进行精确单步潜传播，并引入模型无关的流引导潜插值技术。该技术在无需额外训练下加速去噪，可与任意视频扩散模型（VDM）无缝集成。我们的FGDVI相较现有最先进方法在流扭曲误差E_warp上取得10%的显著提升。我们的全面实验验证了FGDVI的优越性能，为先进视频修复提供有前景的方向。代码与详细结果将公开于https://github.com/NevSNev/FGDVI。
引用
@article{arxiv.2311.15368,
title = {Flow-Guided Diffusion for Video Inpainting},
author = {Bohai Gu and Yongsheng Yu and Heng Fan and Libo Zhang},
journal= {arXiv preprint arXiv:2311.15368},
year = {2025}
}
备注
This paper has been withdrawn as a new iteration of the work has been developed, which includes significant improvements and refinements based on this submission. The withdrawal is made to ensure academic integrity and compliance with publication standards. If you are interested, please refer to the updated work at arXiv:2412.00857