Grouping by Center: Predicting Centripetal Offsets for the Bottom-up Human Pose Estimation

Lei Jin, Xiaojuan Wang, Xuecheng Nie, Luoqi Liu, Yandong Guo, Jian Zhao

Abstract

We introduce Grouping by Center, a novel grouping approach for the bottom-up human pose estimation, which detects human joint first and then does grouping. The grouping strategy is the critical factor for the bottom-up pose estimation. To increase the conciseness and accuracy, we propose to use the center of the body as a grouping clue. More concretely, we predict the offsets from the keypoints to the body centers. Keypoints with aligned shifted results will be grouped as one person. However, the multi-scale variance of people can affect the prediction of the grouping clue, which has been neglected in previous research. To resolve the scale variance of the offset, we put forward a Multi-scale Translation Layer and an iterative refinement. Furthermore, we scheme a greedy grouping strategy with a dynamic threshold due to the various scales of instances. Through a comprehensive comparison, our framework is validated to be effective and practical. We also lay out the state-of-the-art performance revolving the bottom-up multi-person pose estimation on the MS-COCO dataset and the CrowdPose dataset.
BibTeX
@article{jin2023grouping,
  author = {Lei Jin and Xiaojuan Wang and Xuecheng Nie and Luoqi Liu and Yandong Guo and Jian Zhao},
  title = {{Grouping by Center: Predicting Centripetal Offsets for the Bottom-up Human Pose Estimation}},
  journal = {IEEE Trans. Multimedia},
  year = {2023},
  doi = {10.1109/tmm.2022.3159111},
}

Loading related content...

Figure