Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images

Valentin Gabeur 1 Jean-Sébastien Franco 2 Xavier Martin 1 Cordelia Schmid 1, 3 Gregory Rogez 1, 4
1 Thoth - Apprentissage de modèles à partir de données massives
LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
2 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper, we tackle the problem of 3D human shape estimation from single RGB images. While the recent progress in convolutional neural networks has allowed impressive results for 3D human pose estimation, estimating the full 3D shape of a person is still an open issue. Model-based approaches can output precise meshes of naked under-cloth human bodies but fail to estimate details and un-modelled elements such as hair or clothing. On the other hand, non-parametric volumetric approaches can potentially estimate complete shapes but, in practice, they are limited by the resolution of the output grid and cannot produce detailed estimates. In this work, we propose a non-parametric approach that employs a double depth map to represent the 3D shape of a person: a visible depth map and a "hidden" depth map are estimated and combined , to reconstruct the human 3D shape as done with a "mould". This representation through 2D depth maps allows a higher resolution output with a much lower dimension than voxel-based volumetric representations. Additionally , our fully derivable depth-based model allows us to efficiently incorporate a discriminator in an adversar-ial fashion to improve the accuracy and "humanness" of the 3D output. We train and quantitatively validate our approach on SURREAL and on 3D-HUMANS, a new photore-alistic dataset made of semi-synthetic in-house images annotated with 3D ground truth surfaces.
Document type :
Conference papers
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.inria.fr/hal-02242795
Contributor : Thoth Team <>
Submitted on : Thursday, August 1, 2019 - 5:51:22 PM
Last modification on : Sunday, August 4, 2019 - 1:02:08 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02242795, version 1

Collections

INRIA | LJK | UGA

Citation

Valentin Gabeur, Jean-Sébastien Franco, Xavier Martin, Cordelia Schmid, Gregory Rogez. Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images. ICCV 2019, Oct 2019, Seoul, South Korea. ⟨hal-02242795⟩

Share

Metrics

Record views

59

Files downloads

353