Saved in:
Bibliographic Details
Main Authors: Zhang, He, Ren, Shenghao, Yuan, Haolei, Zhao, Jianhui, Li, Fan, Sun, Shuangpeng, Liang, Zhenghao, Yu, Tao, Shen, Qiu, Cao, Xun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.17610
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911819970379776
author Zhang, He
Ren, Shenghao
Yuan, Haolei
Zhao, Jianhui
Li, Fan
Sun, Shuangpeng
Liang, Zhenghao
Yu, Tao
Shen, Qiu
Cao, Xun
author_facet Zhang, He
Ren, Shenghao
Yuan, Haolei
Zhao, Jianhui
Li, Fan
Sun, Shuangpeng
Liang, Zhenghao
Yu, Tao
Shen, Qiu
Cao, Xun
contents Foot contact is an important cue for human motion capture, understanding, and generation. Existing datasets tend to annotate dense foot contact using visual matching with thresholding or incorporating pressure signals. However, these approaches either suffer from low accuracy or are only designed for small-range and slow motion. There is still a lack of a vision-pressure multimodal dataset with large-range and fast human motion, as well as accurate and dense foot-contact annotation. To fill this gap, we propose a Multimodal MoCap Dataset with Vision and Pressure sensors, named MMVP. MMVP provides accurate and dense plantar pressure signals synchronized with RGBD observations, which is especially useful for both plausible shape estimation, robust pose fitting without foot drifting, and accurate global translation tracking. To validate the dataset, we propose an RGBD-P SMPL fitting method and also a monocular-video-based baseline framework, VP-MoCap, for human motion capture. Experiments demonstrate that our RGBD-P SMPL Fitting results significantly outperform pure visual motion capture. Moreover, VP-MoCap outperforms SOTA methods in foot-contact and global translation estimation accuracy. We believe the configuration of the dataset and the baseline frameworks will stimulate the research in this direction and also provide a good reference for MoCap applications in various domains. Project page: https://metaverse-ai-lab-thu.github.io/MMVP-Dataset/.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17610
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors
Zhang, He
Ren, Shenghao
Yuan, Haolei
Zhao, Jianhui
Li, Fan
Sun, Shuangpeng
Liang, Zhenghao
Yu, Tao
Shen, Qiu
Cao, Xun
Computer Vision and Pattern Recognition
Foot contact is an important cue for human motion capture, understanding, and generation. Existing datasets tend to annotate dense foot contact using visual matching with thresholding or incorporating pressure signals. However, these approaches either suffer from low accuracy or are only designed for small-range and slow motion. There is still a lack of a vision-pressure multimodal dataset with large-range and fast human motion, as well as accurate and dense foot-contact annotation. To fill this gap, we propose a Multimodal MoCap Dataset with Vision and Pressure sensors, named MMVP. MMVP provides accurate and dense plantar pressure signals synchronized with RGBD observations, which is especially useful for both plausible shape estimation, robust pose fitting without foot drifting, and accurate global translation tracking. To validate the dataset, we propose an RGBD-P SMPL fitting method and also a monocular-video-based baseline framework, VP-MoCap, for human motion capture. Experiments demonstrate that our RGBD-P SMPL Fitting results significantly outperform pure visual motion capture. Moreover, VP-MoCap outperforms SOTA methods in foot-contact and global translation estimation accuracy. We believe the configuration of the dataset and the baseline frameworks will stimulate the research in this direction and also provide a good reference for MoCap applications in various domains. Project page: https://metaverse-ai-lab-thu.github.io/MMVP-Dataset/.
title MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.17610