Back to Academic Research
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
SpecificationValue
Parametersundisclosed
Taskvideo-generation
Modalitytext, video, 3d
LicenseOther/Custom
Typeopen-weights

✨ Key Features

  • 3D motion generation from 2D supervision
  • No 3D ground truth required
  • Monocular video pose extraction

🔗 Resources


📜 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

open-weights

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