Academic Research / Technion, NVIDIA /
VIVideoMDM
Open WeightsVideo Gentextvideo3dUpdated July 15, 2026
VideoMDM
Model Overview
VideoMDM is a undisclosed-parameter model developed by Academic Research. Released on 2026-07-15.
📊 Quick Specs
Specification Table
| Specification | Value |
|---|---|
| Parameters | undisclosed |
| Task | video-generation |
| Modality | text, video, 3d |
| License | Other/Custom |
| Type | open-weights |
✨ Key Features
- 3D motion generation from 2D supervision
- No 3D ground truth required
- Monocular video pose extraction
🔗 Resources
- GitHub: Repository
- Paper: arXiv
- Website: Project Page
📜 License & Access
Other/Custom — See repository for specific license details.
Key Features
3D motion generation from 2D supervision
Feature 01✦
No 3D ground truth required
Feature 02✦
Monocular video pose extraction
Feature 03✦
You might also want to compare
Verified Sources
Tags
3d-motionvideo-generation2d-supervision
Model Specs
Parameters
Undisclosed
Context Window
undisclosed
License
Other/Custom
Deployment
self-hostable
Resources & Links
Curator Notes
Partially enriched via migration on 2026-07-25. Manual review recommended.
Compare Specs
Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.
Compare Model