cvlab-columbia/zero123

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

45
/ 100
Emerging

Builds on image-conditioned Stable Diffusion, fine-tuned on Objaverse renderings with explicit camera pose conditioning to enable novel view synthesis and 3D reconstruction from single images. Integrates with downstream frameworks like Threestudio and Stable-Dreamfusion for NeRF-based 3D optimization, while addressing the Janus problem through synthetic training data with ground-truth viewpoint annotations rather than relying on text-to-image priors.

3,032 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

3,032

Forks

215

Language

Python

License

MIT

Last pushed

Dec 05, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cvlab-columbia/zero123"

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