测试时指导足矣：基于扩散指导的快速图像和视频编辑
When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance
AI总结：
本文提出通过测试时指导实现高效的图像和视频编辑，理论分析并扩展了现有方法，证明测试时指导能与训练时方法媲美甚至超越。
摘要：
文本驱动的图像和视频编辑可以自然地转化为修复问题，其中遮蔽区域被重建以保持与观察内容和编辑提示的一致性。最近在扩散和流模型中的测试时指导进展为该任务提供了系统框架；然而，现有方法依赖于成本高昂的向量-雅可比积（VJP）计算来近似不可行的指导项，限制了其实际应用。基于Moufad等人（2025）最近的工作，我们提供了对其VJP-free近似的理论洞察，并大幅扩展了其经验评估到大规模图像和视频编辑基准。我们的结果表明，仅测试时指导即可实现与训练时方法相当甚至在某些情况下更优的性能。
英文摘要：
Text-driven image and video editing can be naturally cast as inpainting problems, where masked regions are reconstructed to remain consistent with both the observed content and the editing prompt. Recent advances in test-time guidance for diffusion and flow models provide a principled framework for this task; however, existing methods rely on costly vector--Jacobian product (VJP) computations to approximate the intractable guidance term, limiting their practical applicability. Building upon the recent work of Moufad et al. (2025), we provide theoretical insights into their VJP-free approximation and substantially extend their empirical evaluation to large-scale image and video editing benchmarks. Our results demonstrate that test-time guidance alone can achieve performance comparable to, and in some cases surpass, training-based methods.
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。
