Estimating the 3D shape of objects from monocular images is a well-established and challenging task in the computer vision field. Further challenges arise when highly deformable objects, such as human faces or bodies, are considered. In this work, we address the problem of estimating the 3D shape of a human body from single images. In particular, we provide a solution to the problem of estimating the shape of the body when the subject is wearing clothes. This is a highly challenging scenario as loose clothes might hide the underlying body shape to a large extent. To this aim, we make use of a parametric 3D body model, the SMPL, whose parameters describe the body pose and shape of the body. Our main intuition is that the shape parameters associated with an individual should not change whether the subject is wearing clothes or not. To improve the shape estimation under clothing, we train a deep convolutional network to regress the shape parameters from a single image of a person. To increase the robustness to clothing, we build our training dataset by associating the shape parameters of a "minimally clothed" person to other samples of the same person wearing looser clothes. Experimental validation shows that our approach can more accurately estimate body shape parameters with respect to state-of-the-art approaches, even in the case of loose clothes.

Monocular 3D Body Shape Reconstruction under Clothing / Ferrari, Claudio; Casini, Leonardo; Berretti, Stefano; Del Bimbo, Alberto. - In: JOURNAL OF IMAGING. - ISSN 2313-433X. - ELETTRONICO. - 7:(2021), pp. 12.257-12.268. [10.3390/jimaging7120257]

Monocular 3D Body Shape Reconstruction under Clothing

Ferrari, Claudio;Berretti, Stefano;Del Bimbo, Alberto
2021

Abstract

Estimating the 3D shape of objects from monocular images is a well-established and challenging task in the computer vision field. Further challenges arise when highly deformable objects, such as human faces or bodies, are considered. In this work, we address the problem of estimating the 3D shape of a human body from single images. In particular, we provide a solution to the problem of estimating the shape of the body when the subject is wearing clothes. This is a highly challenging scenario as loose clothes might hide the underlying body shape to a large extent. To this aim, we make use of a parametric 3D body model, the SMPL, whose parameters describe the body pose and shape of the body. Our main intuition is that the shape parameters associated with an individual should not change whether the subject is wearing clothes or not. To improve the shape estimation under clothing, we train a deep convolutional network to regress the shape parameters from a single image of a person. To increase the robustness to clothing, we build our training dataset by associating the shape parameters of a "minimally clothed" person to other samples of the same person wearing looser clothes. Experimental validation shows that our approach can more accurately estimate body shape parameters with respect to state-of-the-art approaches, even in the case of loose clothes.
2021
7
257
268
Goal 9: Industry, Innovation, and Infrastructure
Ferrari, Claudio; Casini, Leonardo; Berretti, Stefano; Del Bimbo, Alberto
File in questo prodotto:
File Dimensione Formato  
jimaging-07-00257-v2.pdf

Accesso chiuso

Descrizione: Documento finale
Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: DRM non definito
Dimensione 6.24 MB
Formato Adobe PDF
6.24 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1289636
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact