tr3e/InterGen

[IJCV 2024] InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions

32
/ 100
Emerging

Employs a diffusion-based architecture with explicit world-frame motion representation to capture spatial relations between two performers, incorporating novel regularization terms to enforce interaction constraints. Supports diverse downstream tasks including person-to-person generation, motion inbetweening, and trajectory control through text conditioning. Includes the InterHuman dataset (107M frames of paired skeletal motion with natural language descriptions) and inference pipeline compatible with SMPL skeletal format.

312 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

312

Forks

26

Language

Python

License

Last pushed

Jul 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tr3e/InterGen"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.