This repository constains the codes and ShapeNet-Skeleton.zip datasets for the Paper.

This implementation uses Pytorch and TensorFlow.

Implementation details

For each stage, please follow the README.md under the Skeleton_inference/Volume_refinement/Mesh_refinement folder.

Fast demo

• Skeleton inference from the RGB images, and then extract coarse meshes from refined volumes.

python demo_im2mesh.py

• Reuse the input images to deform coarse meshes for surface fitting.

python demo_deform.py

Citing this work

If you find this work useful in your research, please consider citing:

@InProceedings{Tang_2019_CVPR,
author = {Tang, Jiapeng and Han, Xiaoguang and Pan, Junyi and Jia, Kui and Tong, Xin},
title = {A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}

Contact

If you have any questions, please feel free to contact with Tang Jiapeng msjptang@mail.scut.edu.cn.