3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Poster Communications Year :

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

Abstract

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.
019-020.pdf (2.62 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

Cite

X 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⟩
148 View
76 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More