Multi-Person Pose Estimation

本文综述了人体姿态估计领域的最新研究,包括实时多人二维姿态估计、密集人体姿态估计、密集人体姿态估计在野外环境中的应用等。介绍了多种姿态估计算法如OpenPose、AlphaPose、Pose Proposal Networks及DensePose,并提供了开源代码资源。

论文:
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields(openpose)
https://arxiv.org/pdf/1611.08050.pdf

RMPE: Regional Multi-Person Pose Estimation(AlphaPose)
http://mvig.sjtu.edu.cn/research/alphapose/rmpe.pdf

Pose Proposal Networks
http://openaccess.thecvf.com/content_ECCV_2018/papers/Sekii_Pose_Proposal_Networks_ECCV_2018_paper.pdf

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
https://arxiv.org/pdf/1812.00324.pdf

DensePose: DensePose: Dense Human Pose Estimation In The Wild
https://arxiv.org/pdf/1802.00434.pdf

开源代码:
openpose
https://github.com/CMU-Perceptual-Computing-Lab/openpose

openpose-plus
https://github.com/tensorlayer/openpose-plus

AlphaPose
https://github.com/MVIG-SJTU/AlphaPose/tree/pytorch

DensePose (3D)
https://github.com/facebookresearch/DensePose

其他:
Simple Baselines for Human Pose Estimation and Tracking

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值