Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Jing, Zeng, Ailing, Lu, Shunlin, Cai, Yuanhao, Zhang, Ruimao, Wang, Haoqian, Zhang, Lei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929225089417216
author Lin, Jing
Zeng, Ailing
Lu, Shunlin
Cai, Yuanhao
Zhang, Ruimao
Wang, Haoqian
Zhang, Lei
author_facet Lin, Jing
Zeng, Ailing
Lu, Shunlin
Cai, Yuanhao
Zhang, Ruimao
Wang, Haoqian
Zhang, Lei
contents In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions. Moreover, they are primarily collected from limited laboratory scenes with textual descriptions manually labeled, which greatly limits their scalability. To overcome these limitations, we develop a whole-body motion and text annotation pipeline, which can automatically annotate motion from either single- or multi-view videos and provide comprehensive semantic labels for each video and fine-grained whole-body pose descriptions for each frame. This pipeline is of high precision, cost-effective, and scalable for further research. Based on it, we construct Motion-X, which comprises 15.6M precise 3D whole-body pose annotations (i.e., SMPL-X) covering 81.1K motion sequences from massive scenes. Besides, Motion-X provides 15.6M frame-level whole-body pose descriptions and 81.1K sequence-level semantic labels. Comprehensive experiments demonstrate the accuracy of the annotation pipeline and the significant benefit of Motion-X in enhancing expressive, diverse, and natural motion generation, as well as 3D whole-body human mesh recovery.
format Preprint
id arxiv_https___arxiv_org_abs_2307_00818
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Lin, Jing
Zeng, Ailing
Lu, Shunlin
Cai, Yuanhao
Zhang, Ruimao
Wang, Haoqian
Zhang, Lei
Computer Vision and Pattern Recognition
In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions. Moreover, they are primarily collected from limited laboratory scenes with textual descriptions manually labeled, which greatly limits their scalability. To overcome these limitations, we develop a whole-body motion and text annotation pipeline, which can automatically annotate motion from either single- or multi-view videos and provide comprehensive semantic labels for each video and fine-grained whole-body pose descriptions for each frame. This pipeline is of high precision, cost-effective, and scalable for further research. Based on it, we construct Motion-X, which comprises 15.6M precise 3D whole-body pose annotations (i.e., SMPL-X) covering 81.1K motion sequences from massive scenes. Besides, Motion-X provides 15.6M frame-level whole-body pose descriptions and 81.1K sequence-level semantic labels. Comprehensive experiments demonstrate the accuracy of the annotation pipeline and the significant benefit of Motion-X in enhancing expressive, diverse, and natural motion generation, as well as 3D whole-body human mesh recovery.
title Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.00818