We Taught an AI to Edit Video Motion

Jia-Bin Huang · Beginner ·📄 Research Papers Explained ·5mo ago
We present Edit-by-Track—a framework that enables precise video motion editing via 3D point tracks. Reference: Yao-Chih Lee, Zhoutong Zhang, Jiahui Huang, Jui-Hsien Wang, Joon-Young Lee, Jia-Bin Huang, Eli Shechtman, Zhengqi Li Generative Video Motion Editing with 3D Point Tracks arXiv 2025 https://arxiv.org/abs/2512.02015 Check out the project page for more results: https://edit-by-track.github.io/ 00:00 Introduction 00:29 Edit-by-Track 00:53 Object removal 01:30 Shape deformation 02:02 Multi-subject editing 02:23 Dynamic view synthesis 02:53 Fine-grained control 03:18 Handling partial tracks 03:52 3D editing 04:20 Model design 06:01 Training data 07:18 Limitations
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
The ABCs of reading medical research and review papers these days
Learn to critically evaluate medical research papers by accepting nothing at face value, believing no one blindly, and checking everything
Medium · LLM
 ⚡
#1 DevLog Meta-research: I Got Tired of Tab Chaos While Reading Research Papers.
Learn to manage research paper tabs efficiently and apply meta-research techniques to improve productivity
Dev.to AI
 ⚡
How to Set Up a Karpathy-Style Wiki for Your Research Field
Learn to set up a Karpathy-style wiki for your research field to organize and share knowledge effectively
Medium · AI
 ⚡
The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap
Scientific knowledge may be stuck in a local minimum, hindering optimal progress, and understanding this concept is crucial for advancing research
ArXiv cs.AI

Chapters (12)

Introduction
0:29 Edit-by-Track
0:53 Object removal
1:30 Shape deformation
2:02 Multi-subject editing
2:23 Dynamic view synthesis
2:53 Fine-grained control
3:18 Handling partial tracks
3:52 3D editing
4:20 Model design
6:01 Training data
7:18 Limitations
Up next
Microsoft Research Forum | Season 2, Episode 4
Microsoft Research
Watch →