TRACE: 视频中基于首帧轨迹引导的对象运动编辑
TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance
AI总结：
本文提出TRACE框架，通过单帧锚点设计轨迹并合成一致的编辑视频，解决对象运动路径编辑问题，实现更协调、真实且可控的视频编辑。
摘要：
我们研究视频中对象运动路径编辑，目标是改变目标对象轨迹同时保持原始场景内容。不同于以往主要操控外观或依赖点跟踪轨迹控制的方法，尤其在摄像机运动视频中用户难以提供轨迹，我们提出一种实用易用的方法。我们提出TRACE框架，允许用户在单个锚点帧设计期望轨迹，然后合成时间一致的编辑视频。我们的方法采用两阶段流程：跨视角运动转换模块将首帧路径设计映射到相机运动下的帧对齐框轨迹，以及运动条件视频重合成模块遵循这些轨迹再生对象，同时保持输入视频的其余内容。在多样化的现实视频实验中，我们的方法产生比最近的图像到视频和视频到视频方法更协调、真实且可控的运动编辑。
英文摘要：
We study object motion path editing in videos, where the goal is to alter a target object's trajectory while preserving the original scene content. Unlike prior video editing methods that primarily manipulate appearance or rely on point-track-based trajectory control, which is often challenging for users to provide during inference, especially in videos with camera motion, we offer a practical, easy-to-use approach to controllable object-centric motion editing. We present Trace, a framework that enables users to design the desired trajectory in a single anchor frame and then synthesizes a temporally consistent edited video. Our approach addresses this task with a two-stage pipeline: a cross-view motion transformation module that maps first-frame path design to frame-aligned box trajectories under camera motion, and a motion-conditioned video re-synthesis module that follows these trajectories to regenerate the object while preserving the remaining content of the input video. Experiments on diverse real-world videos show that our method produces more coherent, realistic, and controllable motion edits than recent image-to-video and video-to-video 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。
