Gaussian Splatting
Original 3D Gaussian Splatting implementation for real-time radiance field rendering.
About
3D Gaussian Splatting from Inria and the Max Planck Institute is the original implementation of real-time radiance field rendering using a set of optimized 3D Gaussians. It reconstructs a scene from multiple photos with training measured in minutes and renders novel views at high frame rates, avoiding the slow neural networks of earlier radiance-field methods. It underpins many later 3D generation tools. Released for research use.
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)
- 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.