Tetrahedron Splatting for 3D Generation,
Chun Gu, Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang
Arxiv preprint
Official implementation of "Tetrahedron Splatting for 3D Generation".
git clone https://github.com/fudan-zvg/tet-splatting.git --recursive
conda create -n tetsplatting python=3.9
conda activate tetsplatting
# install pytorch (e.g. cuda 11.7)
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
# install other denpendencies
pip install -r requirements.txtYou can also refer to threestudio or RichDreamer for preparing the environment.
Download pretrained weights:
python tools/download_nd_models.py
# copy 256_tets file for dmtet.
cp ./pretrained_models/Damo_XR_Lab/Normal-Depth-Diffusion-Model/256_tets.npz ./load/tets/
# link your huggingface models to ./pretrained_models/huggingface
cd pretrained_models && ln -s ~/.cache/huggingface ./# Run a single prompt
python3 ./run_tetsplatting.py -t $prompt -o $output --gpus $GPU
# Run from prompt list
# e.g. bash ./scripts/tetsplatting/run_batch.sh 0 1 ./prompts_dmtet.txt 0
bash ./scripts/tetsplatting/run_batch.sh $start_id $end_id ${prompts_dmtet.txt} ${GPU}This work is built on many amazing research works:
@inproceedings{gu2024tetrahedron,
title={Tetrahedron Splatting for 3D Generation},
author={Gu, Chun and Yang, Zeyu and Pan, Zijie and Zhu, Xiatian and Zhang, Li},
booktitle={NeurIPS},
year={2024}
}