TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance
Quynh Phung, Long Mai, Cusuh Ham, Feng Liu, Jia-Bin Huang, Aniruddha Mahapatra

TL;DR
This paper introduces TRACE, a user-friendly video editing framework that allows for precise object motion editing by designing trajectories in a single frame, ensuring realistic and coherent results even with camera motion.
Contribution
The paper presents a novel two-stage pipeline for object motion editing that simplifies user control and improves realism over existing methods.
Findings
Produces more coherent and realistic motion edits
Handles camera motion effectively during editing
Outperforms recent image-to-video and video-to-video methods
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Advanced Vision and Imaging · Human Motion and Animation
