synthesiaresearch/humanrf

Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"

39
/ 100
Emerging

This project helps 3D artists, animators, and researchers generate highly realistic 3D models of humans in motion from video footage. It takes multi-camera video, masks, and calibration data as input to produce high-fidelity neural radiance fields. The primary users are professionals in computer graphics, visual effects, and academic research who need to create or analyze dynamic human forms.

493 stars. No commits in the last 6 months.

Use this if you need to create extremely lifelike digital representations of moving people for visual effects, virtual reality, or advanced animation projects.

Not ideal if you only need static 3D models or are working with limited computational resources, as it's designed for high-fidelity dynamic capture.

3D-animation visual-effects computer-graphics motion-capture virtual-production
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

493

Forks

30

Language

Python

License

Last pushed

Sep 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/synthesiaresearch/humanrf"

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