Work

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

Year: 2019

Type: conference-paper

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 ground truth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in1,2.

Source: IEEE/CVF International Conference on Computer Vision (ICCV)

DOI: 10.1109/iccv.2019.01023

Authors: Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Institutions: Seoul National University, Kwangwoon University

Language: English

Topic: Human Pose and Action Recognition

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion

Awards: G1647711588, G4855398066