Zero-1-to-3
Novel view synthesis from a single image using diffusion model conditioning.
About
Zero-1-to-3 from Columbia University synthesizes novel views of an object from a single image by conditioning a diffusion model on a relative camera viewpoint, enabling zero-shot 3D reconstruction from one 2D photo. The repository releases several checkpoints fine-tuned on Objaverse for different training lengths, trading zero-shot generalization against fit to training data. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- 3D Model Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- License
- Apache-2.0
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Open-source 3D reconstruction pipeline based on photogrammetry.
Convolutional Reconstruction Model for single-image 3D generation with high-quality textures.
Generates consistent multi-view images from a single view for 3D reconstruction.
Fast single-image to 3D mesh generation using multi-view diffusion and LRM.
Single image to 3D mesh with cross-domain diffusion for consistent multi-view generation.
Fast text-to-3D generation using multi-view diffusion and reconstruction.