HavenFeng/TRUST

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (ECCV2022)

39
/ 100
Emerging

This project helps create realistic 3D digital avatars of faces from a single image. It takes a facial image as input and outputs a 3D head model that accurately represents the person's skin tone, making the avatars more faithful and inclusive. It's ideal for animators, game developers, or researchers working with digital human representations.

160 stars. No commits in the last 6 months.

Use this if you need to generate 3D facial avatars from photos and want to ensure accurate and unbiased skin tone representation.

Not ideal if you need to create 3D models of objects other than faces or if your primary goal is real-time processing rather than high-fidelity reconstruction.

3D-modeling avatar-creation digital-identity computer-graphics facial-reconstruction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

160

Forks

15

Language

Python

License

Last pushed

Jul 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HavenFeng/TRUST"

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