Skip to Main content Skip to Navigation
Conference papers

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

Wen Guo 1 Enric Corona 2 Francesc Moreno-Noguer 2 Xavier Alameda-Pineda 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
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.
Complete list of metadata
Contributor : Team Perception Connect in order to contact the contributor
Submitted on : Monday, October 19, 2020 - 5:17:46 PM
Last modification on : Tuesday, October 19, 2021 - 11:25:54 AM

Links full text


  • HAL Id : hal-02971754, version 1
  • ARXIV : 2010.05302



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. ⟨hal-02971754⟩



Record views