XingangPan/GAN2Shape

Code for GAN2Shape (ICLR2021 oral)

49
/ 100
Emerging

This project helps researchers and artists automatically reconstruct the 3D shape of objects from 2D images created by Generative Adversarial Networks (GANs). You provide a 2D image from a GAN, and it outputs a 3D model, allowing for object rotation and relighting effects. This tool is ideal for those working with synthetic image generation and 3D visualization without needing manual annotations or external 3D models.

576 stars. No commits in the last 6 months.

Use this if you need to extract 3D shape information from 2D GAN-generated images, like faces or cars, for further visualization or analysis without manual 3D modeling.

Not ideal if you are working with real-world photographs or require extremely precise, high-fidelity 3D scans for engineering or medical applications.

3D-reconstruction computer-graphics synthetic-media visual-effects generative-art
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

576

Forks

99

Language

Python

License

MIT

Last pushed

Jul 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/XingangPan/GAN2Shape"

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