For learning purposes, we offer a set of tools and documentation to study 3D Gaussian Splatting. We also plan to provide an unofficial implementation of the paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering.
- Detailed documentation to demonstrate the mathematical principles of 3D Gaussian Splatting
-
Based on our documentation, re-implement 3D Gaussian Splatting.
- Forward on CPU
- Forward on GPU
- Backward on CPU
- Backward on GPU
-
Provide tools for learning 3D Gaussian Splatting.
- A efficient viewer based on pyqtgraph for showing 3D Gaussian data (trained model).
- A demo showing how spherical harmonics work.
pip3 install -r requirements.txt
pip3 install gsplatcu/.
Given camera information, render 3D Gaussian data onto the 2D image.
CPU version.
python3 forword_cpu.py --ply='THE_PATH_OF_YOUR_TRAINED_PLY_FILE'
GPU version.
python3 forword_gpu.py --ply='THE_PATH_OF_YOUR_TRAINED_PLY_FILE'
A efficient 3D Gaussian splatting viewer for showing 3D Gaussian data.
python3 gaussian_viewer.py --ply='THE_PATH_OF_YOUR_TRAINED_PLY_FILE'
A demo showing how spherical harmonics work.
python3 sh_demo.py
"The ground truth Earth image is modified from URL. By Solar System Scope. Licensed under CC-BY-4.0"