A Sampling Approach to Generating Closely Interacting 3D Pose-pairs from 2D Annotations

Yin, Kangxue, Huang, Hui, Ho, Edmond S. L., Wang, Hao, Komura, Taku, Cohen-Or, Daniel and Zhang, Richard (2019) A Sampling Approach to Generating Closely Interacting 3D Pose-pairs from 2D Annotations. IEEE Transactions on Visualization and Computer Graphics, 25 (6). pp. 2217-2227. ISSN 1077-2626

[img]
Preview
Text
Yin et al - A Sampling Approach to Generating Closely Interacting 3D Pose-pairs from 2D Annotations AAM.pdf - Accepted Version

Download (9MB) | Preview
Official URL: https://doi.org/10.1109/TVCG.2018.2832097

Abstract

We introduce a data-driven method to generate a large number of plausible, closely interacting 3D human pose-pairs, for a given motion category, e.g., wrestling or salsa dance. With much difficulty in acquiring close interactions using 3D sensors, our approach utilizes abundant existing video data which cover many human activities. Instead of treating the data generation problem as one of reconstruction, either through 3D acquisition or direct 2D-to-3D data lifting from video annotations, we present a solution based on Markov Chain Monte Carlo (MCMC) sampling. With a focus on efficient sampling over the space of close interactions, rather than pose spaces, we develop a novel representation called interaction coordinates (IC) to encode both poses and their interactions in an integrated manner. Plausibility of a 3D pose-pair is then defined based on the ICs and with respect to the annotated 2D pose-pairs from video. We show that our sampling-based approach is able to efficiently synthesize a large volume of plausible, closely interacting 3D pose-pairs which provide a good coverage of the input 2D pose-pairs.

Item Type: Article
Uncontrolled Keywords: Closely interacting 3D human poses, data generation and augmentation, MCMC sampling
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 04 Jun 2018 15:55
Last Modified: 31 Jul 2021 13:20
URI: http://nrl.northumbria.ac.uk/id/eprint/34473

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics