River-Zhang/SIFU

[CVPR 2024 Highlight] Official repository for paper "SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction"

38
/ 100
Emerging

This tool helps artists, designers, and animators create detailed 3D models of people, complete with clothing, from just a single photograph. You input an image of a person, and it outputs a high-quality 3D digital model that can be used for 3D printing, building virtual scenes, or editing textures. It is especially useful for anyone needing realistic digital doubles.

268 stars. No commits in the last 6 months.

Use this if you need to generate a realistic 3D model of a clothed person from a single image for applications like animation, virtual fashion design, or digital content creation.

Not ideal if you primarily need to reconstruct naked human bodies or if you prefer to work with multiple camera angles and scans for maximum precision.

3D-modeling character-design virtual-reality animation digital-fashion
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

268

Forks

13

Language

Python

License

MIT

Last pushed

Sep 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/River-Zhang/SIFU"

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