English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map

Malik, J., Abdelaziz, I., Elhayek, A., Shimada, S., Ali, S. A., Golyanik, V., et al. (2020). HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map. Retrieved from https://arxiv.org/abs/2004.01588.

Item is

Basic

show hide
Genre: Paper
Latex : {HandVoxNet}: {D}eep Voxel-Based Network for {3D} Hand Shape and Pose Estimation from a Single Depth Map

Files

show Files
hide Files
:
arXiv:2004.01588.pdf (Preprint), 3MB
Name:
arXiv:2004.01588.pdf
Description:
File downloaded from arXiv at 2021-02-03 11:20
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Malik, Jameel1, Author
Abdelaziz, Ibrahim1, Author
Elhayek, Ahmed1, Author
Shimada, Soshi2, Author              
Ali, Sk Aziz1, Author
Golyanik, Vladislav2, Author              
Theobalt, Christian2, Author              
Stricker, Didier1, Author
Affiliations:
1External Organizations, ou_persistent22              
2Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: 3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. The state-of-the-art methods directly regress 3D hand meshes from 2D depth images via 2D convolutional neural networks, which leads to artefacts in the estimations due to perspective distortions in the images. In contrast, we propose a novel architecture with 3D convolutions trained in a weakly-supervised manner. The input to our method is a 3D voxelized depth map, and we rely on two hand shape representations. The first one is the 3D voxelized grid of the shape which is accurate but does not preserve the mesh topology and the number of mesh vertices. The second representation is the 3D hand surface which is less accurate but does not suffer from the limitations of the first representation. We combine the advantages of these two representations by registering the hand surface to the voxelized hand shape. In the extensive experiments, the proposed approach improves over the state of the art by 47.8% on the SynHand5M dataset. Moreover, our augmentation policy for voxelized depth maps further enhances the accuracy of 3D hand pose estimation on real data. Our method produces visually more reasonable and realistic hand shapes on NYU and BigHand2.2M datasets compared to the existing approaches.

Details

show
hide
Language(s): eng - English
 Dates: 2020-04-032020
 Publication Status: Published online
 Pages: 10 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 2004.01588
URI: https://arxiv.org/abs/2004.01588
BibTex Citekey: Malik2004.01588
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show