TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918411299192832 |
|---|---|
| author | Phung, Quynh Mai, Long Ham, Cusuh Liu, Feng Huang, Jia-Bin Mahapatra, Aniruddha |
| author_facet | Phung, Quynh Mai, Long Ham, Cusuh Liu, Feng Huang, Jia-Bin Mahapatra, Aniruddha |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25707 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance Phung, Quynh Mai, Long Ham, Cusuh Liu, Feng Huang, Jia-Bin Mahapatra, Aniruddha Computer Vision and Pattern Recognition 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. |
| title | TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.25707 |