PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation
10.1109/WACV48630.2021.00284
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/366320
Tipus de documentText en actes de congrés
Data publicació2021
EditorInstitute of Electrical and Electronics Engineers (IEEE)
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
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.
Descripció
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
CitacióGuo, W. [et al.]. PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation. A: IEEE Winter Conference on Applications of Computer Vision. "2021 IEEE Winter Conference on Applications of Computer Vision: 5-9 January 2021, virtual event: proceedings". Institute of Electrical and Electronics Engineers (IEEE), 2021, p. 2795-2805. ISBN 978-1-66540-477-8. DOI 10.1109/WACV48630.2021.00284.
ISBN978-1-66540-477-8
Versió de l'editorhttps://ieeexplore.ieee.org/document/9423075
Col·leccions
- IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [576]
- ROBiri - Grup de Percepció i Manipulació Robotitzada de l'IRI - Ponències/Comunicacions de congressos [252]
- Doctorat en Automàtica, Robòtica i Visió - Ponències/Comunicacions de congressos [166]
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
2419-PI-Net_-Po ... lar-3D-Pose-Estimation.pdf | 4,159Mb | Visualitza/Obre |