PG-SAG

PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping

Tengfei Wang*, Xin Wang*, Yongmao Hou, Yiwei Xu, Wendi Zhang, ZongqianZhan**.

Project Page | arXiv

Installation

The repository contains submodules, thus please check it out with

# SSH
git clone git@github.com:TFwang-9527/PG-SAG.git
cd PG-SAG

conda create -n pg-sag python=3.8
conda activate pg-sag

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 #replace your cuda version
pip install -r requirements.txt
pip install submodules/diff-plane-rasterization
pip install submodules/simple-knn

Training

python train.py -s data_path -m out_path --max_abs_split_points 0 --opacity_cull_threshold 0.05

Rendering and Extract Mesh

python render.py -m out_path --max_depth 500.0 --voxel_size 0.01

Acknowledgements

This project is built upon 3DGS, PGSR, adrgaussian and GauUscene . respectively. We thank all the authors for their great work and repos.