HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling


Zhongang Cai*
Daxuan Ren*
Ailing Zeng*
Zhengyu Lin*
Tao Yu*
Wenjia Wang*

Xiangyu Fan
Yang Gao
Yifan Yu
Liang Pan
Fangzhou Hong
Mingyuan Zhang

Chen Change Loy
Lei Yang^
Ziwei Liu^

Shanghai Artificial Intelligence Laboratory
S-Lab, Nanyang Technological University

SenseTime Research
The Chinese University of Hong Kong
Tsinghua University

* co-first authors
^ co-corresponding authors

ECCV 2022 (Oral)




Download v1.0



Reconstruction Subset
(HuMMan-Recon)



Motion Generation Subset
(HuMMan-MoGen)
[Comming Soon]


3D Perception Subset
(HuMMan-Point)
[Comming Soon]



Updates

[2023-04-25] Release of manually annotated masks for color images in the test split

[2023-02-27] Downloads are organized by modalities, links have been updated

[2023-01-23] Release of textured meshes and toolbox.

[2023-01-23] Minor fixes on the mask data, download links have been updated.

[2023-01-11] Release of HuMMan v1.0: Reconstruction Subset.

[2022-10-27] We presented HuMMan as an oral paper at ECCV'22 (Tel Aviv, Israel).

[2022-08] Release of HuMMan v0.1 (no longer available, please use v1.0).



Register for future updates!



Overview


4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. With the advances of new sensors and algorithms, there is an increasing demand for more versatile datasets. In this work, we contribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 human subjects, 400k sequences and 60M frames. HuMMan has several appealing properties: 1) multi-modal data and annotations including color images, point clouds, keypoints, SMPL parameters, and textured meshes; 2) popular mobile device is included in the sensor suite; 3) a set of 500 actions, designed to cover fundamental movements; 4) multiple tasks such as action recognition, pose estimation, parametric human recovery, and textured mesh reconstruction are supported and evaluated. Extensive experiments on HuMMan voice the need for further study on challenges such as fine-grained action recognition, dynamic human mesh reconstruction, point cloud-based parametric human recovery, and cross-device domain gaps.




Scale and Modalities





Action Set




Subject Examples





Full Text



[Preprint]



License

HuMMan is under S-Lab License v1.0.



Citation

@inproceedings{cai2022humman,
  title={{HuMMan}: Multi-modal 4d human dataset for versatile sensing and modeling},
  author={Cai, Zhongang and Ren, Daxuan and Zeng, Ailing and Lin, Zhengyu and Yu, Tao and Wang, Wenjia and Fan,
          Xiangyu and Gao, Yang and Yu, Yifan and Pan, Liang and Hong, Fangzhou and Zhang, Mingyuan and
          Loy, Chen Change and Yang, Lei and Liu, Ziwei},
  booktitle={17th European Conference on Computer Vision, Tel Aviv, Israel, October 23--27, 2022,
             Proceedings, Part VII},
  pages={557--577},
  year={2022},
  organization={Springer}
}