Prior-less 3D Human Shape Reconstruction with an Earth Mover’s Distance Informed CNN

Zhang, Jingtian, Shum, Hubert, McCay, Kevin and Ho, Edmond (2019) Prior-less 3D Human Shape Reconstruction with an Earth Mover’s Distance Informed CNN. In: Proceedings - MIG 2019: ACM Conference on Motion, Interaction, and Games: Newcastle upon Tyne, England, October 28-30, 2019. Association for Computing Machinery, New York, p. 44. ISBN 9781450369947

[img]
Preview
Text
Zhang et al - Prior-less 3D Human Shape Reconstruction with an Earth Mover's Distance Informed CNN AAM.pdf - Accepted Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1145/3359566.3364694

Abstract

We propose a novel end-to-end deep learning framework, capable of 3D human shape reconstruction from a 2D image without the need of a 3D prior parametric model. We employ a “prior-less” representation of the human shape using unordered point clouds. Due to the lack of prior information, comparing the generated and ground truth point clouds to evaluate the reconstruction error is challenging. We solve this problem by proposing an Earth Mover’s Distance (EMD) function to find the optimal mapping between point clouds. Our experimental results show that we are able to obtain a visually accurate estimation of the 3D human shape from a single 2D image, with some inaccuracy for heavily occluded parts.

Item Type: Book Section
Uncontrolled Keywords: Human Surface Reconstruction, Deep Learning, CNN, Earth Mover’s Distance
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 01 Oct 2019 11:23
Last Modified: 14 Aug 2020 09:00
URI: http://nrl.northumbria.ac.uk/id/eprint/40942

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics