arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.07111cs.CVcs.AIcs.LGcs.MM
收藏

基于扩散模型的视频编辑:综述

Diffusion Model-Based Video Editing: A Survey

College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)

Wenhao Sun, Rong-Cheng Tu, Jingyi Liao, Dacheng Tao

AI总结:

该综述系统梳理了基于扩散模型的视频编辑技术的理论基础、方法分类、新兴应用,通过新基准V2VBench完成对比,并指出未来研究的挑战与方向。

摘要:

扩散模型(DMs)的快速发展极大推动了图像与视频应用的进步,让“所想即所见”成为现实。其中,视频编辑领域受到广泛关注,相关研究活动迅速增长,因此有必要对现有文献进行全面系统的梳理。本文综述了基于扩散模型的视频编辑技术,涵盖理论基础与实际应用。我们首先概述了扩散模型的数学公式以及图像领域的关键方法。随后,我们依据核心技术的内在关联对视频编辑方法进行分类,梳理其发展脉络。本文还深入探讨了新兴应用,包括基于点的编辑和姿态引导的人体视频编辑。此外,我们借助新提出的V2VBench(视频到视频基准)进行了全面的对比分析。在现有进展的基础上,本文最后总结了当前面临的挑战以及未来研究的潜在方向。

英文摘要:

The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality. Among these, video editing has gained substantial attention and seen a swift rise in research activity, necessitating a comprehensive and systematic review of the existing literature. This paper reviews diffusion model-based video editing techniques, including theoretical foundations and practical applications. We begin by overviewing the mathematical formulation and image domain's key methods. Subsequently, we categorize video editing approaches by the inherent connections of their core technologies, depicting evolutionary trajectory. This paper also dives into novel applications, including point-based editing and pose-guided human video editing. Additionally, we present a comprehensive comparison using our newly introduced V2VBench. Building on the progress achieved to date, the paper concludes with ongoing challenges and potential directions for future research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑