High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization
  • Python 98.4%
  • Jupyter Notebook 1%
  • Shell 0.6%
Find a file
2025-11-27 00:33:53 +01:00
bash_scripts init 2025-11-27 00:33:53 +01:00
configs init 2025-11-27 00:33:53 +01:00
datasets init 2025-11-27 00:33:53 +01:00
exp_code init 2025-11-27 00:33:53 +01:00
external init 2025-11-27 00:33:53 +01:00
scripts init 2025-11-27 00:33:53 +01:00
third_party/diff_rasterization_w_d init 2025-11-27 00:33:53 +01:00
utils init 2025-11-27 00:33:53 +01:00
viz_scripts init 2025-11-27 00:33:53 +01:00
.gitignore init 2025-11-27 00:33:53 +01:00
README.md init 2025-11-27 00:33:53 +01:00
requirements.txt init 2025-11-27 00:33:53 +01:00

RGB-D Gaussian Splatting SLAM

Installation

Prerequisites

  • Python 3.10
  • CUDA 11.8 or compatible version
  • uv package manager

Environment Setup with uv

Create a virtual environment and install all dependencies:

# Create virtual environment with Python 3.10
uv venv --python 3.10

Activate the virtual environment

source .venv/bin/activate

Install all dependencies

uv pip install -r requirements.txt

Install Gaussian Rasterization Package

After installing the base dependencies, install the custom Gaussian rasterization package:

uv pip install submodules/diff_rasterization_w_d --no-build-isolation
uv pip install git+ssh://git@github.com/cvg/LightGlue.git@b1cd942