English

Hybrid model for Single-Stage Multi-Person Pose Estimation

Computer Vision and Pattern Recognition 2023-06-21 v2

Abstract

In general, human pose estimation methods are categorized into two approaches according to their architectures: regression (i.e., heatmap-free) and heatmap-based methods. The former one directly estimates precise coordinates of each keypoint using convolutional and fully-connected layers. Although this approach is able to detect overlapped and dense keypoints, unexpected results can be obtained by non-existent keypoints in a scene. On the other hand, the latter one is able to filter the non-existent ones out by utilizing predicted heatmaps for each keypoint. Nevertheless, it suffers from quantization error when obtaining the keypoint coordinates from its heatmaps. In addition, unlike the regression one, it is difficult to distinguish densely placed keypoints in an image. To this end, we propose a hybrid model for single-stage multi-person pose estimation, named HybridPose, which mutually overcomes each drawback of both approaches by maximizing their strengths. Furthermore, we introduce self-correlation loss to inject spatial dependencies between keypoint coordinates and their visibility. Therefore, HybridPose is capable of not only detecting densely placed keypoints, but also filtering the non-existent keypoints in an image. Experimental results demonstrate that proposed HybridPose exhibits the keypoints visibility without performance degradation in terms of the pose estimation accuracy.

Keywords

Cite

@article{arxiv.2305.01167,
  title  = {Hybrid model for Single-Stage Multi-Person Pose Estimation},
  author = {Jonghyun Kim and Bosang Kim and Hyotae Lee and Jungpyo Kim and Wonhyeok Im and Lanying Jin and Dowoo Kwon and Jungho Lee},
  journal= {arXiv preprint arXiv:2305.01167},
  year   = {2023}
}
R2 v1 2026-06-28T10:23:02.478Z