cvlab-columbia/zero123
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)
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.
Stars
3,032
Forks
215
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...