TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 45 of its 52 references that are in the map. First posted on arXiv 26 Mar 2026.
Builds on
45 of 52 references.
References · 45
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
- 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
- 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
- 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
- 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
- 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
- 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
- 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
- 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 568
- 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 530
33 more
- 2023CoTracker: It is Better to Track Togethercited by 516
- 2025VACE: All-in-One Video Creation and Editingcited by 467
- 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 463
- 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editingcited by 462
- 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
- 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
- 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Modelscited by 284
- 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
- 2023Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translationcited by 253
- 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
- 2023Tracking Anything with Decoupled Video Segmentationcited by 197
- 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfercited by 194
- 2023Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Modelscited by 135
- 2024Boximator: Generating Rich and Controllable Motions for Video Synthesiscited by 107
- 2025HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generationcited by 84
- 2025VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Controlcited by 83
- 2024ReVideo: Remake a Video with Motion and Content Controlcited by 74
- 2024Trajectory Attention for Fine-grained Video Motion Controlcited by 63
- 2025MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidancecited by 60
- 2025MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generationcited by 50
- 2024UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editingcited by 47
- 2025Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidancecited by 45
- 2024LeviTor: 3D Trajectory Oriented Image-to-Video Synthesiscited by 39
- 2024Generative Omnimatte: Learning to Decompose Video into Layerscited by 38
- 2024Generative Video Propagationcited by 36
- 2023Fine-grained Controllable Video Generation via Object Appearance and Contextcited by 18
- 2025O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editingcited by 10
- 2025GenCompositor: Generative Video Compositing with Diffusion Transformercited by 9
- 2026PISCO: Precise Video Instance Insertion with Sparse Controlcited by 9
- 2025Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxycited by 8
- 2025FreeViS: Training-free Video Stylization with Inconsistent Referencescited by 6
- 2024VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editingcited by 2
- 2025Neural Atlas Graphs for Dynamic Scene Decomposition and Editingcited by 2
Built on by
Citing papers per year: 2026: 3.
3 papers.