English

MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation

Computer Vision and Pattern Recognition 2020-03-31 v1

Abstract

Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts (1) a generic fusion model shared by all cameras, and (2) lightweight camera-dependent transformations. Furthermore, the generic model is learned from many cameras by a meta-learning style algorithm to maximize its adaptation capability to various camera poses. We observe in experiments that MetaFuse finetuned on the public datasets outperforms the state-of-the-arts by a large margin which validates its value in practice.

Keywords

Cite

@article{arxiv.2003.13239,
  title  = {MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation},
  author = {Rongchang Xie and Chunyu Wang and Yizhou Wang},
  journal= {arXiv preprint arXiv:2003.13239},
  year   = {2020}
}

Comments

Accepted to CVPR2020

R2 v1 2026-06-23T14:31:24.595Z