RMPE: Regional Multi-person Pose Estimation

Shanghai Jiaotong University, Tencent Inc.
(* corresponding author: lu-cw@cs.sjtu.edu.cn)


Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve a 17% increase in mAP over the state-of-the-art methods on the MPII (multi person) dataset. Our model and source codes are publicly available.


Code(research purpose only)

Our source code is available on Github, including:

  • Training/test code
  • Pretrained model
  • Evaluation code

If you use this code in your research, please cite this paper.


Download the paper here.


            Title = {{RMPE}: Regional Multi-person Pose Estimation},
            Author = {Haoshu Fang, Shuqin Xie, Yuwing Tai and Cewu Lu },
            Journal = {arXiv preprint arXiv:1612.00137},
            Year = {2016}

Example Results

Browse more results in the paper or use our github code.