Abstract
Recently, 3D hand pose estimation methods taking point cloud as input show the most advanced performance. We present a new 3D deep learning hand pose estimation network for an unordered point cloud. Our approach utilizes EdgeConv layer as the basic element, where an attention embedding version EdgeConv layer is proposed for feature extraction in hand pose estimation task. To improve the result, we design a hand pose improvement network that inputs points whose are in the neighbor of the estimated fingers and outputs a rectify hand pose. We evaluate our method on several famous datasets to prove that our method can get excellent result compared to some most advanced methods.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
