Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
- 20 April 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 26 (8) , 2560-2575
Abstract
Human bodies exhibit various shapes for different identities or poses, but the body shape has certain similarities in structure and thus can be embedded in a low-dimensional space. This article presents an autoencoder-like network architecture to learn disentangled shape and pose embedding specifically for the 3D human body. This is inspired by recent progress of deformation-based latent representation learning. To improve the reconstruction accuracy, we propose a hierarchical reconstruction pipeline for the disentangling process and construct a large dataset of human body models with consistent connectivity for the learning of the neural network. Our learned embedding can not only achieve superior reconstruction accuracy but also provide great flexibility in 3D human body generation via interpolation, bilinear interpolation, and latent space sampling. The results from extensive experiments demonstrate the powerfulness of our learned 3D human body embedding in various applications.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61672481)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (2018495)
- NTU Data Science and Artificial Intelligence Research Center (M4082285)
- MoE Tier-2 (2016-T2-2-065, 2017-T2-1-076)
- National Research Foundation Singapore
This publication has 51 references indexed in Scilit:
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Sparse localized deformation componentsACM Transactions on Graphics, 2013
- Coregistration: Simultaneous Alignment and Modeling of Articulated 3D Shape2012
- Lie Bodies: A Manifold Representation of 3D Human Shape2012
- MovieReshapeACM Transactions on Graphics, 2010
- Parametric reshaping of human bodies in imagesACM Transactions on Graphics, 2010
- A Statistical Model of Human Pose and Body ShapeComputer Graphics Forum, 2009
- SCAPEACM Transactions on Graphics, 2005
- The space of human body shapesACM Transactions on Graphics, 2003
- Generalized Procrustes AnalysisPsychometrika, 1975