/Awesome-PoseEstimation

This a collecttion of papers for pose estimation.

Awesome-Pose Estimation Awesome


This is a collection of papers for pose estimation.

Table of Contents

Papers

Top-Down Approach

RMPE: Regional Multi-person Pose Estimation. (AlphaPose)
Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu
ICCV2017 [paper] [code]


Deep High-Resolution Representation Learning for Human Pose Estimation.
Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang
CVPR2019 [paper] [code] Html


Pose Recognition with Cascade Transformers.
Ke Li, Shijie Wang, Xiang Zhang, Yifan Xu, Weijian Xu, Zhuowen Tu
CVPR2021 [paper] [code] Html


TransPose: Keypoint Localization via Transformer.
Sen Yang, Zhibin Quan, Mu Nie, Wankou Yang
ICCV2021 [paper] [code] Html


TokenPose: Learning Keypoint Tokens for Human Pose Estimation.
Yanjie Li, Shoukui Zhang, Zhicheng Wang, Sen Yang, Wankou Yang, Shu-Tao Xia, Erjin Zhou
ICCV2021 [paper] [code] Html


TFPose: Direct Human Pose Estimation with Transformers.
Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang
arXiv2021 [paper] [code] Html


HRFormer: High-Resolution Transformer for Dense Prediction.
Yuhui Yuan, Rao Fu, Lang Huang, Weihong Lin, Chao Zhang, Xilin Chen, Jingdong,Wang
NIPS2021 [paper] [code]


ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation.
Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao
arXiv2022 [paper] [code]

Bottom-Up Approach


DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation.
Leonid Pishchulin, Eldar Insafutdinov, Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, Peter Gehler , Bernt Schiele
CVPR2016 [paper] [code]


DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model.
Leonid Pishchulin, Eldar Insafutdinov, Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, Peter Gehler and Bernt Schiele
ECCV2016 [paper] [code]


Openpose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.
Zhe Cao Tomas Simon Shih-En Wei Yaser Sheikh
CVPR2017 [paper] [code]


Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression.
Zigang Geng, Ke Sun, Bin Xiao, Zhaoxiang Zhang, Jingdong Wang
CVPR2021 [paper] [code] Html

End-To-End Approach


End-to-End Trainable Multi-Instance Pose Estimation with Transformers
Lucas Stoffl, Maxime Vidal, Alexander Mathis
arXiv2021 [paper] [code] Html


End-to-End Multi-Person Pose Estimation with Transformers.
Dahu Shi, Xing Wei, Liangqi Li, Ye Ren, Wenming Tan
CVPR2022 [paper] [code] Html

Datasets


COCO Datasets [paper] [website]


MPII Human Pose Dataset [paper] [website]


LSP (Leeds Sports Pose) Dataset [paper] [website]


FLIC (Frames labeled In Cinema) Dataset [paper] [website]


PoseTrack Datasets [paper] [website]