Hand Pose Understanding With Large-Scale Photo-Realistic Rendering Dataset

doi:10.1109/TIP.2021.3070439

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 三维可视计算

	Hand Pose Understanding With Large-Scale Photo-Realistic Rendering Dataset
	Deng, Xiaoming 3; Zhang, Yinda 4; Shi, Jian 5; Zhu, Yuying 3; Cheng, Dachuan 6; Zuo, Dexin 3; Cui, Zhaopeng 7; Tan, Ping 1,8; Chang, Liang 2; Wang, Hongan 3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2021
卷号	30 页码:4275-4290
关键词	Three-dimensional displays Annotations Pose estimation Task analysis Color Image color analysis Rendering (computer graphics) Hand pose estimation photo-realistic synthetic dataset physical-based rendering multi-task CNN
ISSN号	1057-7149
DOI	10.1109/TIP.2021.3070439
通讯作者	Deng, Xiaoming(xiaoming@iscas.ac.cn)
英文摘要	Hand pose understanding is essential to applications such as human computer interaction and augmented reality. Recently, deep learning based methods achieve great progress in this problem. However, the lack of high-quality and large-scale dataset prevents the further improvement of hand pose related tasks such as 2D/3D hand pose from color and depth from color. In this paper, we develop a large-scale and high-quality synthetic dataset, PBRHand. The dataset contains millions of photo-realistic rendered hand images and various ground truths including pose, semantic segmentation, and depth. Based on the dataset, we firstly investigate the effect of rendering methods and used databases on the performance of three hand pose related tasks: 2D/3D hand pose from color, depth from color and 3D hand pose from depth. This study provides insights that photo-realistic rendering dataset is worthy of synthesizing and shows that our new dataset can improve the performance of the state-of-the-art on these tasks. This synthetic data also enables us to explore multi-task learning, while it is expensive to have all the ground truth available on real data. Evaluations show that our approach can achieve state-of-the-art or competitive performance on several public datasets.
资助项目	National Key Research and Development Program of China[2019YFC1521100] ; Distinguished Young Researcher Program, Institute of Software, Chinese Academy of Sciences
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000640713600009
资助机构	National Key Research and Development Program of China ; Distinguished Young Researcher Program, Institute of Software, Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44497]
专题	模式识别国家重点实验室_三维可视计算
通讯作者	Deng, Xiaoming
作者单位	1.Alibaba, Hangzhou 310012, Peoples R China 2.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China 3.Chinese Acad Sci, Inst Software, Beijing Key Lab Human Comp Interact, Beijing 100190, Peoples R China 4.Google, Mountain View, CA 94043 USA 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China 7.Zhejiang Univ, State Key Lab CAD&CG, Hangzhou 310058, Peoples R China 8.Simon Fraser Univ, Sch Comp Sci, Burnaby, BC V5A 1S6, Canada
推荐引用方式 GB/T 7714	Deng, Xiaoming,Zhang, Yinda,Shi, Jian,et al. Hand Pose Understanding With Large-Scale Photo-Realistic Rendering Dataset[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:4275-4290.
APA	Deng, Xiaoming.,Zhang, Yinda.,Shi, Jian.,Zhu, Yuying.,Cheng, Dachuan.,...&Wang, Hongan.(2021).Hand Pose Understanding With Large-Scale Photo-Realistic Rendering Dataset.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,4275-4290.
MLA	Deng, Xiaoming,et al."Hand Pose Understanding With Large-Scale Photo-Realistic Rendering Dataset".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):4275-4290.