JANE: Joint Angle Networks Assisting 3D Human Pose Estimation

Jinhuan Wang; Yuzhen Zhao; Xujie Song; Wenzhou Chen; Qi Xuan

ICASSP 2025accepted0 citations

JANE: Joint Angle Networks Assisting 3D Human Pose Estimation

Jinhuan Wang, Yuzhen Zhao, Xujie Song, Wenzhou Chen, Qi Xuan

Abstract

3D human pose estimation (HPE) is crucial due to its extensive applications. While current 3D HPE methods focus on human skeleton topology for accuracy, they often overlook joint angle information, which is vital in 2D-to-3D pose lifting. This paper introduces the Joint Angle Network (JANE) model to leverage joint angle features from 2D poses. We propose an angle graph convolution module to extract joint angle features and a multi-stage parallel fusion module to integrate these features with input image data. Experiments on Human3.6M show that our method improves accuracy by 8.7% and 2.6% over non-spatiotemporal baselines using 2D ground truth and 2D pose detectors, respectively.

BibTeX

@inproceedings{icassp2025_janejointanglene,
  title = {JANE: Joint Angle Networks Assisting 3D Human Pose Estimation},
  author = {Jinhuan Wang and Yuzhen Zhao and Xujie Song and Wenzhou Chen and Qi Xuan},
  booktitle = {ICASSP 2025},
  year = {2025}
}