liangxuy/ReGenNet

[CVPR 2024] Official implementation of the paper "ReGenNet: Towards Human Action-Reaction Synthesis"

33
/ 100
Emerging

This project helps create realistic animations of two people interacting, where one person reacts to the other's actions. You input a sequence of human poses (like from motion capture) for an 'actor' and it generates a corresponding pose sequence for a 'reactor'. This is ideal for animators, game developers, or researchers who need to simulate natural human social interactions.

No commits in the last 6 months.

Use this if you need to automatically generate how one virtual human character would realistically react to the specific movements of another.

Not ideal if you're looking for a tool to generate single-person movements or highly stylized, non-realistic human animations.

3D-animation character-design human-computer-interaction virtual-reality motion-capture-data
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

68

Forks

5

Language

Python

License

MIT

Last pushed

Sep 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/liangxuy/ReGenNet"

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