Hand 3D Keypoint Estimation Application Based on Graph Neural Networks

Xuan Wang; Chunyan Peng; Shilong Chen

doi:10.2991/978-94-6463-742-7_50

<Previous Article In Volume

Next Article In Volume>

Hand 3D Keypoint Estimation Application Based on Graph Neural Networks

Authors

Xuan Wang¹^{, 2}^{, 3}^{, 4}^{, 5}, Chunyan Peng¹^{, 2}^{, 3}^{, 4}^{, 5}^{, *}, Shilong Chen¹^{, 2}

¹School of Computer, Qinghai Normal University, Xining, 810008, Qinghai, China

²The State Key Laboratory of Tibetan Intelligence, Qinghai Normal University, Xining, Qinghai, 810008, China

³Key Laboratory of Tibetan Information Processing, Ministry of Education, Xining, 810008, China

⁴Qinghai Provincial Key Laboratory of Tibetan Information Processing and Machine Translation, Xining, 810008, China

⁵Tibetan Information Processing Engineering Technology Research Center of Qinghai Province, Xining, 810008, China

^*Corresponding author. Email: pcy@qhnu.edu.cn

Corresponding Author

Chunyan Peng

Available Online 31 May 2025.

DOI: 10.2991/978-94-6463-742-7_50 How to use a DOI?
Keywords: Graph Neural Networks; 3D Keypoint Estimation; Hand Pose; Model Deployment; Unreal Engine
Abstract: This paper proposes a hand 3D keypoint estimation application system based on graph neural networks (GNN), providing an intuitive visualization solution for fields like virtual reality, gesture control, and medical rehabilitation. The system takes a single RGB image as input, employs a two-stage model composed of Keypoint R-CNN and GNN to predict 3D keypoint coordinates of the input hand image, and maps the results to a 3D hand model in Unreal Engine through post-processing. Leveraging tools such as ONNX, Unreal Engine NNE, and OpenCV, we implemented a complete engineering pipeline encompassing image acquisition, model inference, and 3D visualization. This validates the deployability and application prospects of the method in real-world scenarios.
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 2025 4th International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2025)
Series: Advances in Intelligent Systems Research
Publication Date: 31 May 2025
ISBN: 978-94-6463-742-7
ISSN: 1951-6851
DOI: 10.2991/978-94-6463-742-7_50 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Xuan Wang
AU  - Chunyan Peng
AU  - Shilong Chen
PY  - 2025
DA  - 2025/05/31
TI  - Hand 3D Keypoint Estimation Application Based on Graph Neural Networks
BT  - Proceedings of the 2025 4th International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2025)
PB  - Atlantis Press
SP  - 524
EP  - 538
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-742-7_50
DO  - 10.2991/978-94-6463-742-7_50
ID  - Wang2025
ER  -

download .riscopy to clipboard