NVlabs/affordance_diffusion

Codes for "Affordance Diffusion: Synthesizing Hand-Object Interactions"

28
/ 100
Experimental

This helps generate realistic images and 3D models of how a human hand might interact with an object. You provide an image of an object, and it produces several examples of hands gripping, holding, or using that object, along with 3D poses of the hand. This is useful for animators, virtual reality content creators, or robotics engineers who need to simulate human-object interactions.

130 stars. No commits in the last 6 months.

Use this if you need to visualize or generate diverse, plausible ways a human hand would interact with a specific object from an image.

Not ideal if you need to analyze real-world video footage of hand-object interactions or require extremely high-fidelity, physically accurate simulations for engineering design.

3D animation virtual reality content creation robotics simulation product design visualization human factors engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

130

Forks

8

Language

Python

License

Last pushed

Nov 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NVlabs/affordance_diffusion"

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