wanmeihuali/taichi_3d_gaussian_splatting

An unofficial implementation of paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering by taichi lang.

44
/ 100
Emerging

This project helps 3D artists, game developers, or virtual reality creators efficiently generate realistic 3D scenes or objects from a set of 2D images. It takes multiple photographs of a scene, a sparse set of 3D points, and camera positions as input. The output is a highly detailed 3D representation that can be rendered from any viewpoint, even new ones, with high visual quality.

744 stars. No commits in the last 6 months.

Use this if you need to create highly realistic, viewable 3D environments or objects from photographs for applications like virtual tours, digital twins, or immersive experiences, and you value efficient scene construction and merging.

Not ideal if your primary goal is to generate simple 3D models for basic animations or if you do not have multiple photographic views and camera pose information of your subject.

3D-reconstruction virtual-reality digital-twins computer-graphics scene-rendering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

744

Forks

73

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/wanmeihuali/taichi_3d_gaussian_splatting"

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