NeurCross: A Neural Approach to Computing Cross Fields for Quad Mesh Generation

Project | Paper

This repository is the official PyTorch implementation of our paper, NeurCross: A Neural Approach to Computing Cross Fields for Quad Mesh Generation, ACM Transactions on Graphics (SIGGRAPH 2025).

Requirements

• python 3.7
• CUDA 11.7
• Pytorch 1.13.1

Installation

git clone https://github.com/QiujieDong/NeurCross.git
cd NeurCross

Overfitting

cd quad_mesh
python train_quad_mesh.py

All parameters are set in the quad_mesh_args.py.

Extraction

The extractor is from libigl and libQEx.

Cite

If you find our work useful for your research, please consider citing our paper.

@article{Dong2025NeurCross,
author={Dong, Qiujie and Wen, Huibiao and Xu, Rui and Chen, Shuangmin and Zhou, Jiaran and Xin, Shiqing and Tu, Changhe and Komura, Taku and Wang, Wenping},
title={NeurCross: A Neural Approach to Computing Cross Fields for Quad Mesh Generation},
journal={ACM Trans. Graph.},
publisher={Association for Computing Machinery},
address={New York, NY, USA},
year={2025},
volume={44},
number={4},
url={https://doi.org/10.1145/3731159},
doi={10.1145/3731159}
}

Acknowledgments

Our code is inspired by NeurCADRecon and SIREN. We would like to thank the authors of libigl and libQEx.