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

被引:5
|
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 Human Pose Estimation With Adversarial Learning
    Meng, Wenming
    Hu, Tao
    Shuai, Li
    2019 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND VISUALIZATION (ICVRV), 2019, : 93 - 99
  • [32] ASCS-Reinforcement Learning: A Cascaded Framework for Accurate 3D Hand Pose Estimation
    Chen, Mingqi
    Shuang, Feng
    Li, Shaodong
    Liu, Xi
    PROCEEDINGS OF THE 2023 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2023, 2023, : 335 - 342
  • [33] A Comprehensive Study on Deep Learning-Based 3D Hand Pose Estimation Methods
    Chatzis, Theocharis
    Stergioulas, Andreas
    Konstantinidis, Dimitrios
    Dimitropoulos, Kosmas
    Daras, Petros
    APPLIED SCIENCES-BASEL, 2020, 10 (19): : 1 - 27
  • [34] 3D Hand Pose Estimation from RGB Using Privileged Learning with Depth Data
    Yuan, Shanxin
    Stenger, Bjorn
    Kim, Tae-Kyun
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 2866 - 2873
  • [35] Attention-Based Pose Sequence Machine for 3D Hand Pose Estimation
    Guo, Fangtai
    He, Zaixing
    Zhang, Shuyou
    Zhao, Xinyue
    Tan, Jianrong
    IEEE ACCESS, 2020, 8 : 18258 - 18269
  • [36] 3D Hand Shape and Pose Estimation based on 2D Hand Keypoints
    Drosakis, Drosakis
    Argyros, Antonis
    PROCEEDINGS OF THE 16TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2023, 2023, : 148 - 153
  • [37] Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation
    Moon, Gyeongsik
    Choi, Hongsuk
    Lee, Kyoung Mu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 2307 - 2316
  • [38] A Survey on Depth Ambiguity of 3D Human Pose Estimation
    Zhang, Siqi
    Wang, Chaofang
    Dong, Wenlong
    Fan, Bin
    APPLIED SCIENCES-BASEL, 2022, 12 (20):
  • [39] Estimation of 3D human hand poses with structured pose prior
    Guo, Fangtai
    He, Zaixing
    Zhang, Shuyou
    Zhao, Xinyue
    IET COMPUTER VISION, 2019, 13 (08) : 683 - 690
  • [40] Single-Frame Indexing for 3D Hand Pose Estimation
    Carley, Cassandra
    Tomasi, Carlo
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW), 2015, : 493 - 501