arXiv:2603.25707cs.CV2026-03被引 3

用户只需在首帧画轨迹,即可精准控制视频中物体运动路径。

TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance

  • 通过首帧轨迹设计,自动推导全程运动路径
  • 在存在相机运动的复杂视频中仍保持运动一致性
  • 适合需要精确控制物体运动的影视剪辑与动画制作

我们研究视频中目标物体运动路径的编辑问题,目标是在不改变场景内容的前提下,调整目标物体的运动轨迹。与以往主要操控外观或依赖点跟踪的轨迹控制方法不同,这些方法在推理阶段对用户输入要求高,尤其在存在相机运动的视频中难以操作。为此,我们提出Trace框架,使用户仅需在单个锚定帧中绘制期望轨迹,即可合成时间一致的编辑后视频。该方法采用两阶段流程:第一阶段为跨视角运动转换模块,将首帧轨迹设计映射为受相机运动影响下的逐帧边界框轨迹;第二阶段为运动条件视频重生成模块,根据生成轨迹重构物体,同时保留原视频其余内容。在多种真实世界视频上的实验表明,本方法在运动连贯性、真实感和可控性方面均优于近期图像到视频及视频到视频的方法。

原文摘要 · Abstract (English)

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.

视频编辑运动控制轨迹引导

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。