Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Reconstructing Human Body Mesh from Point Clouds by Adversarial GP Network

Boyao Zhou 1, 2 Jean-Sébastien Franco 2 Federica Bogo 1 Bugra Tekin 1 Edmond Boyer 2
2 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : We study the problem of reconstructing the template-aligned mesh for human body estimation from unstructured point cloud data. Recently proposed approaches for shape matching that rely on Deep Neu-ral Networks (DNNs) achieve state-of-the-art results with generic point-wise architectures; but in doing so, they exploit much weaker human body shape and surface priors with respect to methods that explicitly model the body surface with 3D templates. We investigate the impact of adding back such stronger shape priors by proposing a novel dedicated human template matching process, which relies on a point-based, deep autoencoder architecture. We encode surface smoothness and shape coherence with a specialized Gaussian Process layer. Furthermore, we enforce global consistency and improve the generalization capabilities of the model by introducing an adversarial training phase. The choice of these elements is grounded on an extensive analysis of DNNs failure modes in widely used datasets like SURREAL and FAUST. We validate and evaluate the impact of our novel components on these datasets, showing a quantitative improvement over state-of-the-art DNN-based methods, and qualitatively better results.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [2 references]  Display  Hide  Download

https://hal.inria.fr/hal-02977388
Contributor : Boyao Zhou <>
Submitted on : Saturday, October 24, 2020 - 7:17:50 PM
Last modification on : Tuesday, November 24, 2020 - 4:00:09 PM

Files

Identifiers

  • HAL Id : hal-02977388, version 1

Collections

Citation

Boyao Zhou, Jean-Sébastien Franco, Federica Bogo, Bugra Tekin, Edmond Boyer. Reconstructing Human Body Mesh from Point Clouds by Adversarial GP Network. 2020. ⟨hal-02977388⟩

Share

Metrics

Record views

84

Files downloads

214