DreamGaussian
Fast 3D content generation using Gaussian Splatting with mesh extraction.
About
DreamGaussian generates 3D content from text or a single image using generative Gaussian Splatting paired with an efficient mesh extraction step. By replacing slow score-distillation optimization with a Gaussian representation, it produces a textured 3D mesh in roughly two minutes, far faster than methods like DreamFusion. The repository provides the official implementation and instructions. Released under the MIT 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
- MIT
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
CUDA-accelerated Gaussian splatting rasterization library with Python bindings from the Nerfstudio team.
Generates high-resolution textured 3D assets from images or text with separate shape and texture models.
Generates explorable, mesh-exportable 3D worlds from text or image prompts via panoramic proxies.
Roblox's research foundation model that generates 3D shapes from text prompts for game assets.
Reconstructs 3D shape, texture, and layout of objects from a single cluttered real-world photo.
Reconstructs dense 3D scenes from uncalibrated image collections without known camera poses.