3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting - Archive ouverte HAL
Poster De Conférence Année : 2022

3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting

Résumé

We propose a two-stage hybrid method, with no initialization, for 3D human shape and pose estimation from a single depth image, combining the benefits of deep learning and optimization.First, a convolutional neural networkpredicts pixel-wise dense semantic correspondences to a template geometry, in the form of body part segmentation labels and normalized canonical geometry vertex coordinates. Using these two outputs, pixel-to-vertex correspondences are computed in a six-dimensional embedding of the template geometry through nearest neighbor. Second, a parametric shape model (SMPL) is fitted to the depth data by minimizingvertex distances to the input.Extensive evaluation on both real and synthetic humanshape in motiondatasets shows that our methodyields quantitatively and qualitatively satisfactory results and state-of-the-art reconstruction errors.
Fichier principal
Vignette du fichier
postereg2022_schedarvfinal.pdf (791.03 Ko) Télécharger le fichier
019-020.pdf (2.62 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03664189 , version 1 (10-05-2022)

Licence

Identifiants

Citer

Xiaofang Wang, Adnane Boukhayma, Stéphanie Prevost, Eric Desjardin, C Loscos, et al.. 3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting. Eurographics 2022 - 43nd Annual Conference of the European Association for Computer Graphics, Apr 2022, Reims, France. pp.1-2, ⟨10.2312/egp.20221008⟩. ⟨hal-03664189⟩
257 Consultations
380 Téléchargements

Altmetric

Partager

More