Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey

被引:9
|
作者
Ohkawa, Takehiko [1 ]
Furuta, Ryosuke [1 ]
Sato, Yoichi [1 ]
机构
[1] Univ Tokyo, Inst Ind Sci, 4-6-1 Komaba,Meguro Ku, Tokyo 1538505, Japan
关键词
Hand pose estimation; Efficient annotation; Learning with limited labels; TRACKING;
D O I
10.1007/s11263-023-01856-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D hand pose estimation has been an important research area owing to its potential to enable various applications, such as video understanding, AR/VR, and robotics. However, the performance of models is tied to the quality and quantity of annotated 3D hand poses. Under the status quo, acquiring such annotated 3D hand poses is challenging, e.g., due to the difficulty of 3D annotation and the presence of occlusion. To reveal this problem, we review the pros and cons of existing annotation methods classified as manual, synthetic-model-based, hand-sensor-based, and computational approaches. Additionally, we examine methods for learning 3D hand poses when annotated data are scarce, including self-supervised pretraining, semi-supervised learning, and domain adaptation. Based on the study of efficient annotation and learning, we further discuss limitations and possible future directions in this field.
引用
收藏
页码:3193 / 3206
页数:14
相关论文
共 50 条
  • [31] 3D Hand Pose Estimation From Monocular RGB With Feature Interaction Module
    Guo, Shaoxiang
    Rigall, Eric
    Ju, Yakun
    Dong, Junyu
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (08) : 5293 - 5306
  • [32] FingerPoseNet: A finger-level multitask learning network with residual feature sharing for 3D hand pose estimation
    Tewolde, Tekie Tsegay
    Manjotho, Ali Asghar
    Sarker, Prodip Kumar
    Niu, Zhendong
    NEURAL NETWORKS, 2025, 187
  • [33] Accurate and efficient 3D hand pose regression for robot hand teleoperation using a monocular RGB camera
    Gomez-Donoso, Francisco
    Orts-Escolano, Sergio
    Cazorla, Miguel
    EXPERT SYSTEMS WITH APPLICATIONS, 2019, 136 : 327 - 337
  • [34] Excavator 3D pose estimation using deep learning and hybrid datasets
    Assadzadeh, Amin
    Arashpour, Mehrdad
    Li, Heng
    Hosseini, Reza
    Elghaish, Faris
    Baduge, Shanaka
    ADVANCED ENGINEERING INFORMATICS, 2023, 55
  • [35] Dynamic Hand Gesture Recognition Based on 3D Hand Pose Estimation for Human-Robot Interaction
    Gao, Qing
    Chen, Yongquan
    Ju, Zhaojie
    Liang, Yi
    IEEE SENSORS JOURNAL, 2022, 22 (18) : 17421 - 17430
  • [36] Hand Pose Estimation from RGB Images Based on Deep Learning: A Survey
    Liu, Yang
    Jiang, Jie
    Sun, Jiahao
    2021 IEEE 7TH INTERNATIONAL CONFERENCE ON VIRTUAL REALITY (ICVR 2021), 2021, : 82 - 89
  • [37] Region ensemble network: Towards good practices for deep 3D hand pose estimation
    Wang, Guijin
    Chen, Xinghao
    Guo, Hengkai
    Zhang, Cairong
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2018, 55 : 404 - 414
  • [38] 3D Hand Pose Estimation Using Synthetic Data and Weakly Labeled RGB Images
    Cai, Yujun
    Ge, Liuhao
    Cai, Jianfei
    Thalmann, Nadia Magnenat
    Yuan, Junsong
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (11) : 3739 - 3753
  • [39] Hand Pose Estimation Based on 3D Residual Network with Data Padding and Skeleton Steadying
    Ting, Pai-Wen
    Chou, En-Te
    Tang, Ya-Hui
    Fu, Li-Chen
    COMPUTER VISION - ACCV 2018, PT V, 2019, 11365 : 293 - 307
  • [40] Coot optimization based Enhanced Global Pyramid Network for 3D hand pose estimation
    Malavath, Pallavi
    Devarakonda, Nagaraju
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2022, 3 (04):