Back to Search
Start Over
Neural Hand Reconstruction Using A Single RGB Image
- Source :
- Virtual Reality & Intelligent Hardware, Vol 2, Iss 3, Pp 276-289 (2020)
- Publication Year :
- 2020
- Publisher :
- KeAi Communications Co., Ltd., 2020.
-
Abstract
- We present a neural hand reconstruction method for monocular 3D hand pose and shape estimation in this paper. Instead of directly representing hand with 3D data, a novel UV position map is introduced to represent hand pose and shape with 2D data, which maps 3D hand surface points to 2D image space. Furthermore, an encoder-decoder neural network is proposed to infer such UV position map from only single image. To train such network with the lack of ground truth training pairs, we propose a novel MANOReg module which employs MANO model as shape prior to constrain high-dimensional space of UV position map. Both quantitative and qualitative experiments demonstrate the effectiveness of our UV position map representation and MANOReg module.
Details
- Language :
- English
- ISSN :
- 20965796
- Volume :
- 2
- Issue :
- 3
- Database :
- Directory of Open Access Journals
- Journal :
- Virtual Reality & Intelligent Hardware
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.6714998cd21f458996bf9ca58fad890a
- Document Type :
- article
- Full Text :
- https://doi.org/10.1016/j.vrih.2020.05.001