Learning a deep network with spherical part model for 3D hand pose estimation

作者：

Highlights：

• A novel vision-based framework for 3D hand pose estimation is proposed.

• A spherical Part Model is proposed to transform the joint locations to an explicit representation.

• The dataset is expanded by rotating the original images every 45°.

摘要

•A novel vision-based framework for 3D hand pose estimation is proposed.•A spherical Part Model is proposed to transform the joint locations to an explicit representation.•The dataset is expanded by rotating the original images every 45°.

论文关键词：Hand detection,Hand pose estimation,Deep learning,Convolutional neural network,Spherical part model

论文评审过程：Received 15 March 2017, Revised 20 February 2018, Accepted 25 February 2018, Available online 27 February 2018, Version of Record 7 March 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.02.029