hjwdzh / FrameNet

FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image

Source code for the paper:

Jingwei Huang, Yichao Zhou, Thomas Funkhouser, and Leonidas Guibas. FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image, ICCV 2019.

FrameNet Teaser

Usage Pipeline

Experiments

Please refer to src directory for details.

Fun AR Application

Please refer to src/demo directory for details.

Rendering Toolbox

Please try the example from this repo.

Author

© 2019 Jingwei Huang All Rights Reserved

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

@article{huang2019framenet,
  title={FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image},
  author={Huang, Jingwei and Zhou, Yichao and Funkhouser, Thomas and Guibas, Leonidas},
  journal={arXiv preprint arXiv:1903.12305},
  year={2019}
}

About

FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image

License:MIT License


Languages

Language:Python 79.9%Language:C++ 17.4%Language:Shell 1.4%Language:CMake 1.3%