Search code, repositories, users, issues, pull requests...
This project combines the capabilities of DUSt3R and MASt3R for camera parameter estimation and initial point cloud creation with the 3D scene representation efficiency of Gaussian Splatting. The goal is to simplify the process of 3D scene reconstruction and visualization from images without requiring pre-set camera information or specific viewpoint data. You can perform camera estimation and initial point cloud creation using either 00_dust3r_inference.ipynb or 00_mast3r_inference.ipynb. MASt3R requires fewer resources and can handle longer sequences. Follow this with Gaussian splatting using 01_gaussian_splatting_fitting.ipynb.
With the environment activated, run the provided setup script and pass your CUDA version as an argument. This script installs necessary dependencies tailored to your CUDA version:
