hjwdzh / TextureNet

TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes

Home Page:http://stanford.edu/~jingweih/papers/texturenet/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes

Source code for the paper:

Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Niessner, and Leonidas Guibas. TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes, CVPR 2019 ([Oral Presentation]).

TextureNet Teaser

Usage Pipeline

Data Preparation

Please refer to data directory for details.

Training, Testing and Result Generation

Please refer to src directory for details.

Preparing the Final Results and Evaluation Scores

Please refer to evaluate directory for details.

Author

© 2019 Jingwei Huang All Rights Reserved

IMPORTANT: If you use this code please cite the following in any resulting publication:

@inproceedings{huang2019texturenet,
  title={Texturenet: Consistent local parametrizations for learning from high-resolution signals on meshes},
  author={Huang, Jingwei and Zhang, Haotian and Yi, Li and Funkhouser, Thomas and Nie{\ss}ner, Matthias and Guibas, Leonidas J},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={4440--4449},
  year={2019}
}

About

TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes

http://stanford.edu/~jingweih/papers/texturenet/

License:MIT License


Languages

Language:C++ 90.2%Language:C 4.5%Language:Python 2.1%Language:Cuda 1.2%Language:CMake 1.1%Language:Makefile 0.6%Language:Shell 0.3%