Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

Jia Li, Wen Su, Zengfu Wang
11/24/2019
cs.CV

Official code: hellojialee/Improved-Body-Parts (263 stars, PyTorch, last commit 2022-05-23).

Abstract

We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to hard keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available online.

View on arXivView PDF

Code Implementations(1)

hellojialee/Improved-Body-PartsOfficial100%
PyTorch

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

26340Shell, PythonJan 26, 20194 years ago
apexbottom-updistributedfocal-l2-lossheatmap+7 more

Similar Papers

Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation

90% match2023

ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimation

90% match2026

Cascaded Pyramid Network for Multi-Person Pose Estimation

90% match1 repo7912017

OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

89% match1 repo34.5k2018

Towards High Performance One-Stage Human Pose Estimation

89% match2023

GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation

88% match1 repo192024

Cite this paper

@article{li2019simple,
  title  = {Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation},
  author = {Jia Li and Wen Su and Zengfu Wang},
  year   = {2019},
  eprint = {1911.10529},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1911.10529}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1911.10529.svg)](https://codeofpaper.com/paper/1911.10529)

Discussion