Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.
@article{arxiv.1901.00148,
title = {Rethinking on Multi-Stage Networks for Human Pose Estimation},
author = {Wenbo Li and Zhicheng Wang and Binyi Yin and Qixiang Peng and Yuming Du and Tianzi Xiao and Gang Yu and Hongtao Lu and Yichen Wei and Jian Sun},
journal= {arXiv preprint arXiv:1901.00148},
year = {2019}
}