3D convolutional neural networks for efficient and robust hand pose estimation from single depth images

• Main Authors: Ge, Liuhao, Liang, Hui, Yuan, Junsong, Thalmann, Daniel
• Other Authors: Interdisciplinary Graduate School (IGS)
• Format: Conference or Workshop Item
• Language: English
• Published: 2019
• Subjects: Three-dimensional Displays; Pose Estimation; Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/82836; http://hdl.handle.net/10220/50409
• Institution: Nanyang Technological University

We propose a simple, yet effective approach for real-time hand pose estimation from single depth images using three-dimensional Convolutional Neural Networks (3D CNNs). Image based features extracted by 2D CNNs are not directly suitable for 3D hand pose estimation due to the lack of 3D spatial infor...