Pose2Body: Pose-Guided Human Parts Segmentation

Zhong Li, Xin Chen, Wangyiteng Zhou, Yingliang Zhang, Jingyi Yu

Abstract

Reliable human parts segmentation on 2D images plays an important role in many human-centric computer vision tasks. While significant achievements have been made on human pose estimation, the performance on human parts segmentation remains low. In this paper, we present a novel technique that we call Pose2Body that robustly conducts human parts segmentation based on the pose estimation results. We partition an image into superpixels and set out to assign a segment label to each superpixel most consistent with the pose. We design special feature vectors for every superpixel-label assignment as well as superpixel-superpixel pairs and model optimal labeling as to solve for a conditional random field (CRF). Comprehensive experiments show that our technique achieves substantial improvements over the state-of-the-art solutions.
BibTeX
@inproceedings{li2019pose,
  author = {Zhong Li and Xin Chen and Wangyiteng Zhou and Yingliang Zhang and Jingyi Yu},
  title = {{Pose2Body: Pose-Guided Human Parts Segmentation}},
  booktitle = {ICME},
  year = {2019},
  doi = {10.1109/icme.2019.00116},
}

Loading related content...

Figure