DEHPR: A Diffusion-based End-to-end Hand Pose Reconstruction Network

Authors

Guoqiong Liao, Modern Industry School of Virtual Reality (VR), Jiangxi University of Finance and Economics, Nanchang 330032, China; Jiangxi Tourism and Commerce Vocational College, Nanchang 330100, China
Longjie Huang, School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang 330032, China
Qingxin Li, School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang 330032, China
Jiajun Zhang, Modern Industry School of Virtual Reality (VR), Jiangxi University of Finance and Economics, Nanchang 330032, China
Kefan Chen, Modern Industry School of Virtual Reality (VR), Jiangxi University of Finance and Economics, Nanchang 330032, China

Abstract

Abstract: Traditional methods such as convolutional neural networks (CNNs) and Transformers suffer from strong dependence on large-scale annotated data and limited generalization capability when dealing with hand pose reconstruction in complex scenarios. To address these issues, a diffusion-based end-to-end hand pose reconstruction network (DEHPR) is proposed. This method employs a diffusion model to directly generate and refine 3D predictions, thereby reducing spatial uncertainties inherent in 2D-to-3D modeling paradigms. By incorporating an end-to-end framework that reprojects multiple 3D candidate predictions to select optimal joint positions, the approach ultimately produces accurate hand pose estimations. Comprehensive evaluations conducted on HO3D V2, DexYCB, and FreiHand datasets demonstrate that DEHPR achieves superior performance compared to existing methods. The proposed solution effectively diminishes dependency on large-scale annotated data, mitigates uncertainties in indirect 2D-to-3D modeling from single RGB images, and consequently enhances both accuracy and robustness in hand pose reconstruction.

Recommended Citation

Liao, Guoqiong; Huang, Longjie; Li, Qingxin; Zhang, Jiajun; and Chen, Kefan (2026) "DEHPR: A Diffusion-based End-to-end Hand Pose Reconstruction Network," Journal of System Simulation: Vol. 38: Iss. 1, Article 13.
DOI: 10.16182/j.issn1004731x.joss.25-0863
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss1/13

First Page

174

Last Page

188

CLC

TP391.41

Recommended Citation

Liao Guoqiong, Huang Longjie, Li Qingxin, et al. DEHPR: A Diffusion-based End-to-end Hand Pose Reconstruction Network[J]. Journal of System Simulation, 2026, 38(1): 174-188.

Corresponding Author

Huang Longjie

DOI

10.16182/j.issn1004731x.joss.25-0863