Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 10133-10142

Abstract


Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in (https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE) , (https://github.com/mks0601/3DMPPE_POSENET_RELEASE).

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Moon_2019_ICCV,
author = {Moon, Gyeongsik and Chang, Ju Yong and Lee, Kyoung Mu},
title = {Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}