3D Human Pose Estimation with 2D Human Pose and Depthmap

Zhiheng Zhou*, Yue Cao, Xuanying Zhu, Henry Gardner, Hongdong Li

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


    Three-dimensional human pose estimation models are conventionally based on RGB images or by assuming that accurately-estimated (near to ground truth) 2D human pose landmarks are available. Naturally, such data only contains information about two dimensions, while the 3D poses require the three dimensions of height, width, and depth. In this paper, we propose a new 3D human pose estimation model that takes an estimated 2D pose and the depthmap of the 2D pose as input to estimate 3D human pose. In our system, the estimated 2D pose is obtained from processing an RGB image using a 2D landmark detection network that produces noisy heatmap data. We compare our results with a Simple Linear Model (SLM) of other authors that takes accurately-estimated 2D pose landmarks as input and that has reached the state-of-the-art results for 3D human pose estimate using the Human3.6m dataset. Our results show that our model can achieve better performance than the SLM, and that our model can align the 2D landmark data with the depthmap automatically. We have also tested our network using estimated 2D poses and depthmaps separately. In our model, all three conditions (depthmap+2D pose, depthmap-only and 2D pose-only) are more accurate than the SLM with, surprisingly, the depthmap-only condition being comparable in accuracy with the depthmap+2D pose condition.

    Original languageEnglish
    Title of host publicationNeural Information Processing - 27th International Conference, ICONIP 2020, Proceedings
    EditorsHaiqin Yang, Kitsuchart Pasupa, Andrew Chi-Sing Leung, James T. Kwok, Jonathan H. Chan, Irwin King
    PublisherSpringer Science and Business Media Deutschland GmbH
    Number of pages8
    ISBN (Print)9783030638191
    Publication statusPublished - 2020
    Event27th International Conference on Neural Information Processing, ICONIP 2020 - Bangkok, Thailand
    Duration: 18 Nov 202022 Nov 2020

    Publication series

    NameCommunications in Computer and Information Science
    ISSN (Print)1865-0929
    ISSN (Electronic)1865-0937


    Conference27th International Conference on Neural Information Processing, ICONIP 2020


    Dive into the research topics of '3D Human Pose Estimation with 2D Human Pose and Depthmap'. Together they form a unique fingerprint.

    Cite this