CLOTH3D: Clothed 3D Humans

Authors:

Preprint

5 December 2019

preprint
Published by arXiv in arXiv

DOI:https://doi.org/10.48550/arXiv.1912.02792

Abstract

This work presents CLOTH3D, the first big scale synthetic dataset of 3D clothed human sequences. CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on top of thousands of different pose sequences and body shapes, generating realistic cloth dynamics. We provide the dataset with a generative model for cloth generation. We propose a Conditional Variational Auto-Encoder (CVAE) based on graph convolutions (GCVAE) to learn garment latent spaces. This allows for realistic generation of 3D garments on top of SMPL model for any pose and shape.

Keywords

All Related Versions

This publication has 4 references indexed in Scilit:

Mesh Variational Autoencoders with Edge Contraction Pooling
2020
A Comprehensive Survey on Graph Neural Networks
IEEE Transactions on Neural Networks and Learning Systems, 2020
SimulCap : Single-View Human Performance Capture With Cloth Simulation
2019
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013