NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments

Official implementation of NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments. Provides our pre-trained models, scripts to evalute them, and tools to train framework components from scratch.

⚡ Our NeuralTailor paper was accepted to SIGGRAPH 2022!

Dataset

For training and evaluation, NeuralTailor uses dataset created with Garment-Pattern-Generator.

• Dataset is available from Zenodo: Dataset of 3D Garments with Sewing Patterns

Docs

Provided in ./docs folder

1. Installtion instructions: Installation
2. How to run training and evaluation: Running

Citation

If you are using our system in your research, consider citing our paper.

@article{NeuralTailor2022,
  author = {Korosteleva, Maria and Lee, Sung-Hee},
  title = {NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments},
  year = {2022},
  issue_date = {July 2022},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  volume = {41},
  number = {4},
  doi = {10.1145/3528223.3530179},
  journal = {ACM Trans. Graph.},
  numpages = {16},
  keywords = {structured deep learning, sewing patterns, garment reconstruction}
}

Contact

For bug reports, feature suggestion, and code-related questions, please open an issue.

For other inquires, contact the authors:

• Maria Korosteleva (mariako@kaist.ac.kr) (Main point of contact).

• Sung-Hee Lee (sunghee.lee@kaist.ac.kr).