PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation

(1, 2) , (3) , (3) , (1, 2)
1
2
3

Abstract

Recent literature addressed the monocular 3D pose estimation task very satisfactorily. In these studies, different persons are usually treated as independent pose instances to estimate. However, in many every-day situations, people are interacting, and the pose of an individual depends on the pose of his/her interactees. In this paper, we investigate how to exploit this dependency to enhance current - and possibly future - deep networks for 3D monocular pose estimation. Our pose interacting network, or PI-Net, inputs the initial pose estimates of a variable number of interactees into a recurrent architecture used to refine the pose of the person-of-interest. Evaluating such a method is challenging due to the limited availability of public annotated multi-person 3D human pose datasets. We demonstrate the effectiveness of our method in the MuPoTS dataset, setting the new state-of-the-art on it. Qualitative results on other multi-person datasets (for which 3D pose ground-truth is not available) showcase the proposed PI-Net. PI-Net is implemented in PyTorch and the code will be made available upon acceptance of the paper.

Dates and versions

hal-02971754 , version 1 (19-10-2020)

Identifiers

Cite

Wen Guo, Enric Corona, Francesc Moreno-Noguer, Xavier Alameda-Pineda. PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation. WACV 2021 - IEEE Winter Conference on Applications of Computer vision, Jan 2021, Waikoloa, United States. pp.1-11, ⟨10.1109/WACV48630.2021.00284⟩. ⟨hal-02971754⟩
124 View
9 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More