dc.contributor.authorGe, Liuhao
dc.contributor.authorCai, Yujun
dc.contributor.authorWeng, Junwu
dc.contributor.authorYuan, Junsong
dc.date.accessioned2018-07-16T06:19:57Z
dc.date.available2018-07-16T06:19:57Z
dc.date.issued2018
dc.identifier.urihttp://hdl.handle.net/10220/45084
dc.description.abstractConvolutional Neural Network (CNN) has shown promising results for 3D hand pose estimation in depth images. Different from existing CNN-based hand pose estimation methods that take either 2D images or 3D volumes as the input, our proposed Hand PointNet directly processes the 3D point cloud that models the visible surface of the hand for pose regression. Taking the normalized point cloud as the input, our proposed hand pose regression network is able to capture complex hand structures and accurately regress a low dimensional representation of the 3D hand pose. In order to further improve the accuracy of fingertips, we design a fingertip refinement network that directly takes the neighboring points of the estimated fingertip location as input to refine the fingertip location. Experiments on three challenging hand pose datasets show that our proposed method outperforms state-of-the-art methods.en_US
dc.description.sponsorshipNRF (Natl Research Foundation, S’pore)en_US
dc.description.sponsorshipMOE (Min. of Education, S’pore)en_US
dc.format.extent10 p.en_US
dc.language.isoenen_US
dc.rights© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://openaccess.thecvf.com/content_cvpr_2018/html/Ge_Hand_PointNet_3D_CVPR_2018_paper.html].en_US
dc.subject3D Hand Poseen_US
dc.subjectPose Regressionen_US
dc.titleHand PointNet : 3D hand pose estimation using point setsen_US
dc.typeConference Paper
dc.contributor.conferenceThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018en_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.contributor.schoolInterdisciplinary Graduate School (IGS)en_US
dc.description.versionAccepted versionen_US
dc.contributor.organizationInstitute for Media Innovationen_US
dc.identifier.urlhttp://openaccess.thecvf.com/content_cvpr_2018/html/Ge_Hand_PointNet_3D_CVPR_2018_paper.html


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record