Human Pose Estimation is a fundamental task for many applications in the Computer Vision community and it has been widely investigated in the 2D domain, i.e. intensity images. Therefore, most of the available methods for this task are mainly based on 2D Convolutional Neural Networks and huge manually-annotated RGB datasets, achieving stunning results. In this paper, we propose RefiNet, a multi-stage framework that regresses an extremely-precise 3D human pose estimation from a given 2D pose and a depth map. The framework consists of three different modules, each one specialized in a particular refinement and data representation, i.e. depth patches, 3D skeleton and point clouds. Moreover, we present a new dataset, called Baracca, acquired with RGB, depth and thermal cameras and specifically created for the automotive context. Experimental results confirm the quality of the refinement procedure that largely improves the human pose estimations of off-the-shelf 2D methods.

RefiNet: 3D Human Pose Refinement with Depth Maps / D'Eusanio, Andrea; Pini, Stefano; Borghi, Guido; Vezzani, Roberto; Cucchiara, Rita. - (2021), pp. 2320-2327. (Intervento presentato al convegno 25th International Conference on Pattern Recognition, ICPR 2020 tenutosi a Milan nel 10-15 January 2021) [10.1109/ICPR48806.2021.9412451].

RefiNet: 3D Human Pose Refinement with Depth Maps

Andrea D’Eusanio;Stefano Pini;Guido Borghi;Roberto Vezzani;Rita Cucchiara
2021

Abstract

Human Pose Estimation is a fundamental task for many applications in the Computer Vision community and it has been widely investigated in the 2D domain, i.e. intensity images. Therefore, most of the available methods for this task are mainly based on 2D Convolutional Neural Networks and huge manually-annotated RGB datasets, achieving stunning results. In this paper, we propose RefiNet, a multi-stage framework that regresses an extremely-precise 3D human pose estimation from a given 2D pose and a depth map. The framework consists of three different modules, each one specialized in a particular refinement and data representation, i.e. depth patches, 3D skeleton and point clouds. Moreover, we present a new dataset, called Baracca, acquired with RGB, depth and thermal cameras and specifically created for the automotive context. Experimental results confirm the quality of the refinement procedure that largely improves the human pose estimations of off-the-shelf 2D methods.
2021
25th International Conference on Pattern Recognition, ICPR 2020
Milan
10-15 January 2021
2320
2327
D'Eusanio, Andrea; Pini, Stefano; Borghi, Guido; Vezzani, Roberto; Cucchiara, Rita
RefiNet: 3D Human Pose Refinement with Depth Maps / D'Eusanio, Andrea; Pini, Stefano; Borghi, Guido; Vezzani, Roberto; Cucchiara, Rita. - (2021), pp. 2320-2327. (Intervento presentato al convegno 25th International Conference on Pattern Recognition, ICPR 2020 tenutosi a Milan nel 10-15 January 2021) [10.1109/ICPR48806.2021.9412451].
File in questo prodotto:
File Dimensione Formato  
ICPR_2020_Human_Pose_Estimation_compressed.pdf

Open access

Tipologia: Versione originale dell'autore proposta per la pubblicazione
Dimensione 910.86 kB
Formato Adobe PDF
910.86 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1212262
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 4
social impact