Deakin University
Browse

File(s) under permanent embargo

3D hand pose estimation using simulation and partial-supervision with a shared latent space

conference contribution
posted on 2018-01-01, 00:00 authored by Masoud Abdi, E Abbasnejad, Chee Peng LimChee Peng Lim, Saeid Nahavandi
© 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. Tremendous amounts of expensive annotated data are a vital ingredient for state-of-the-art 3d hand pose estimation. Therefore, synthetic data has been popularized as annotations are automatically available. However, models trained only with synthetic samples do not generalize to real data, mainly due to the gap between the distribution of synthetic and real data. In this paper, we propose a novel method that seeks to predict the 3d position of the hand using both synthetic and partially-labeled real data. Accordingly, we form a shared latent space between three modalities: synthetic depth image, real depth image, and pose. We demonstrate that by carefully learning the shared latent space, we can find a regression model that is able to generalize to real data. As such, we show that our method produces accurate predictions in both semi-supervised and unsupervised settings. Additionally, the proposed model is capable of generating novel, meaningful, and consistent samples from all of the three domains. We evaluate our method qualitatively and quantitively on two highly competitive benchmarks (i.e., NYU and ICVL) and demonstrate its superiority over the state-of-the-art methods. The source code will be made available at https://github.com/masabdi/LSPS.

History

Event

British Machine Vision. Conference (2018 : 29th : Newcastle, England)

Pagination

1 - 16

Publisher

[The Conference]

Location

Newcastle, England

Place of publication

[Newcastle, Eng.]

Start date

2018-09-03

End date

2018-09-06

Language

eng

Publication classification

E1 Full written paper - refereed

Title of proceedings

BMVC 2018 : Proceedings of the 29th British Machine Vision Conference

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC