Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments.
(2014) In IEEE Transactions on Pattern Analysis and Machine Intelligence 36(7). p.1325-1339- Abstract
- We introduce a new dataset, Human3.6M, of 3.6 Million 3D Human poses, acquired by recording the performance of 11 subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next generation of human pose estimation models. Besides increasing the size the current state of the art datasets by several orders of magnitude, we aim to complement such datasets with a diverse set of poses encountered in typical human activities (taking photos, posing, greeting, eating, etc.), with synchronized image, motion capture and depth data, and with accurate 3D body scans of all subjects involved. We also provide mixed reality videos where 3D human models are animated using motion capture data and inserted... (More)
- We introduce a new dataset, Human3.6M, of 3.6 Million 3D Human poses, acquired by recording the performance of 11 subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next generation of human pose estimation models. Besides increasing the size the current state of the art datasets by several orders of magnitude, we aim to complement such datasets with a diverse set of poses encountered in typical human activities (taking photos, posing, greeting, eating, etc.), with synchronized image, motion capture and depth data, and with accurate 3D body scans of all subjects involved. We also provide mixed reality videos where 3D human models are animated using motion capture data and inserted using correct 3D geometry, in complex real environments, viewed with moving cameras, and under occlusion. Finally, we provide large scale statistical models and detailed evaluation baselines for the dataset illustrating its diversity and the scope for improvement by future work in the research community. The dataset and code for the associated large-scale learning models, features, visualization tools, as well as the evaluation server, are available online at http://vision.imar.ro/human3.6m. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4223588
- author
- Ionescu, Catalin ; Papava, Dragos ; Olaru, Vlad and Sminchisescu, Cristian LU
- organization
- publishing date
- 2014
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- 3D human pose estimation, human motion capture data, articulated body modeling, optimization, large scale learning, structured prediction, Fourier kernel approximations
- in
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- volume
- 36
- issue
- 7
- pages
- 1325 - 1339
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- pmid:24344079
- wos:000338209900004
- scopus:84903127719
- ISSN
- 1939-3539
- DOI
- 10.1109/TPAMI.2013.248
- language
- English
- LU publication?
- yes
- additional info
- Published online 12 december 2013
- id
- 6a729909-19b5-4879-9079-1140039117b3 (old id 4223588)
- date added to LUP
- 2016-04-01 10:28:41
- date last changed
- 2022-05-17 23:20:27
@article{6a729909-19b5-4879-9079-1140039117b3,
abstract = {{We introduce a new dataset, Human3.6M, of 3.6 Million 3D Human poses, acquired by recording the performance of 11 subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next generation of human pose estimation models. Besides increasing the size the current state of the art datasets by several orders of magnitude, we aim to complement such datasets with a diverse set of poses encountered in typical human activities (taking photos, posing, greeting, eating, etc.), with synchronized image, motion capture and depth data, and with accurate 3D body scans of all subjects involved. We also provide mixed reality videos where 3D human models are animated using motion capture data and inserted using correct 3D geometry, in complex real environments, viewed with moving cameras, and under occlusion. Finally, we provide large scale statistical models and detailed evaluation baselines for the dataset illustrating its diversity and the scope for improvement by future work in the research community. The dataset and code for the associated large-scale learning models, features, visualization tools, as well as the evaluation server, are available online at http://vision.imar.ro/human3.6m.}},
author = {{Ionescu, Catalin and Papava, Dragos and Olaru, Vlad and Sminchisescu, Cristian}},
issn = {{1939-3539}},
keywords = {{3D human pose estimation; human motion capture data; articulated body modeling; optimization; large scale learning; structured prediction; Fourier kernel approximations}},
language = {{eng}},
number = {{7}},
pages = {{1325--1339}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}},
title = {{Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments.}},
url = {{http://dx.doi.org/10.1109/TPAMI.2013.248}},
doi = {{10.1109/TPAMI.2013.248}},
volume = {{36}},
year = {{2014}},
}