paper 154：姿态估计（Hand Pose Estimation）相关总结

Awesome Works  ！！！！

Table of Contents

  • Conference Papers

    • 2017 ICCV
    • 2017 CVPR
    • 2017 Others
    • 2016 ECCV
    • 2016 CVPR
    • 2016 Others
    • 2015 ICCV
    • 2015 CVPR
    • 2015 Others
    • 2014 CVPR
    • 2014 Others & Before
  • Journal Papers
  • Theses
  • Datasets
  • Challenges
  • Other Related Papers

Evaluation codes

See folder evaluation to get more details about performance evaluation for hand pose estimation.

arXiv Papers

[arXiv:1712.01057] GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB. [PDF]

Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt

[arXiv:1711.10872] Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network. [PDF]

Qi Ye, Tae-Kyun Kim

[arXiv:1711.08996] Dense 3D Regression for Hand Pose Estimation. [PDF]  [Code]

Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao

[arXiv:1711.07399] V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map. [PDF]

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

[arXiv:1708.03416] Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation. [PDF]

Xinghao Chen, Guijin Wang, Hengkai Guo, Cairong Zhang

[arXiv:1707.07248] Towards Good Practices for Deep 3D Hand Pose Estimation. [PDF] [Code]

Hengkai Guo, Guijin Wang, Xinghao Chen, Cairong Zhang

[arXiv:1707.03742] Large-scale Multiview 3D Hand Pose Dataset. [PDF]  [Project Page]

Francisco Gomez-Donoso, Sergio Orts-Escolano and Miguel Cazorla

[arXiv:1705.09606] End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth data. [PDF]

Meysam Madadi, Sergio Escalera, Xavier Baro, Jordi Gonzalez

[arXiv:1704.02224] Hand3D: Hand Pose Estimation using 3D Neural Network. [PDF]  [Project Page]

Xiaoming Deng*, Shuo Yang*, Yinda Zhang*, Ping Tan, Liang Chang, Hongan Wang

[arXiv:1612.00596] Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects. [PDF]

Yu Zhang, Chi Xu, Li Cheng

[arXiv:1610.07214] 3D Hand Pose Tracking and Estimation Using Stereo Matching. [PDF]

Jiawei Zhang, Jianbo Jiao, Mingliang Chen, Liangqiong Qu, Xiaobin Xu, Qingxiong Yang

Conference Papers

2017 ICCV

Learning to Estimate 3D Hand Pose from Single RGB Images. [PDF]  [Project Page]   [Code]

Christian Zimmermann, Thomas Brox

Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor. [PDF] [Project Page]

Franziska Mueller, Dushyant Mehta, Oleksandr Sotnychenko, Srinath Sridhar, Dan Casas, Christian Theobalt

Robust Hand Pose Estimation during the Interaction with an Unknown Object. [PDF] [Supp] [Project Page]

Chiho Choi, Sang Ho Yoon, Chin-Ning Chen, Karthik Ramani

Learning Hand Articulations by Hallucinating Heat Distribution. [PDF] [Supp]  [Project Page]

Chiho Choi, Sangpil Kim, Karthik Ramani

[Hands17 Workshop] Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo. [PDF]

Paschalis Panteleris, Antonis Argyros

[Hands17 Workshop] DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation. [PDF] [Project Page] [Code]

Markus Oberweger and Vincent Lepetit

[Hands17 Workshop] Hand Pose Estimation Using Deep Stereovision and Markov-chain Monte Carlo. [PDF]

Rilwan Remilekun Basaru, Chris Child, Eduardo Alonso, Greg Slabaugh

2017 CVPR

Hand Keypoint Detection in Single Images using Multiview Bootstrapping. [PDF] [Project Page] [Code]

Tomas Simon, Hanbyul Joo, Iain Matthews, Yaser Sheikh

Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation. [PDF] [Code]

Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao

Big Hand 2.2M Benchmark: Hand Pose Data Set and State of the Art Analysis. [PDF]

Shanxin Yuan*, Qi Ye*, Bjorn Stenger, Siddhand Jain, Tae-Kyun Kim

3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation from Single Depth Images.[PDF] [Project Page]

Liuhao Ge, Hui Liang, Junsong Yuan and Daniel Thalmann

2017 Others

[2017 3DV] How to Refine 3D Hand Pose Estimation from Unlabelled Depth Data? [PDF]

Endri Dibra*, Thomas Wolf*, Cengiz ?ztireli, Markus Gross

[2017 ICIP] Region Ensemble Network: Improving Convolutional Network for Hand Pose Estimation. [PDF]  [Code]

Hengkai Guo, Guijin Wang, Xinghao Chen, Cairong Zhang, Fei Qiao, Huazhong Yang

[2017 ICIP] A Hand Pose Tracking Benchmark from Stereo Matching. [PDF]  [Project Page]

Jiawei Zhang, Jianbo Jiao, Mingliang Chen, Liangqiong Qu, Xiaobin Xu, and Qingxiong Yang

[2017 SIGGRAPH Asia] Articulated distance fields for ultra-fast tracking of hands interacting. [PDF]

Jonathan Taylor*, Vladimir Tankovich*, Danhang Tang*, Cem Keskin*, David Kim, Philip Davidson, Adarsh Kowdle, Shahram Izadi

[2017 SIGGRAPH Asia] Online Generative Model Personalization for Hand Tracking. [PDF]  [Project Page]

Anastasia Tkach*, Andrea Tagliasacchi*, Edoardo Remelli, Mark Pauly, Andrew Fitzgibbon

[2017 SIGGRAPH Asia] Embodied Hands: Modeling and Capturing Hands and Bodies Together. [PDF]  [Project Page]

Javier Romero*, Dimitrios Tzionas* and Michael J. Black

[2017 BMVC] Hand Pose Learning: Combining Deep Learning and Hierarchical Refinement for 3D Hand Pose Estimation. [PDF]

Min-Yu Wu, Ya Hui Tang, Pai-Wei Ting and Li-Chen Fu

[2017 BMVC] Generative 3D Hand Tracking with Spatially Constrained Pose Sampling. [PDF] [Project Page]

Konstantinos Roditakis, Alexandros Makris and Antonis Argyros

[2017 ICRA] Learning a deep network with spherical part model for 3D hand pose estimation. [PDF]

Tzu-Yang Chen, Pai-Wen Ting, Min-Yu Wu, Li-Chen Fu

[2017 FG] Occlusion aware hand pose recovery from sequences of depth images. [PDF] [Slide]

Meysam Madadi, Sergio Escalera, Alex Carruesco Llorens, Carlos Andujar, Xavier Baro, Jordi Gonzalez

[2017 FG] 3D Hand-Object Pose Estimation from Depth with Convolutional Neural Networks. [PDF] [Project Page]

Duncan Goudie, Aphrodite Galata

2016 ECCV

Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation. [PDF] [Project Page]

Qi Ye*, Shanxin Yuan*, Tae-Kyun Kim

Hand Pose Estimation from Local Surface Normals. [PDF]

Chengde Wan, Angela Yao, and Luc Van Gool

Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input. [PDF] [Project Page]

Srinath Sridhar, Franziska Mueller, Michael Zollh?fer, Dan Casas, Antti Oulasvirta, Christian Theobalt

2016 Others

[2016 ICPR] Depth-based 3D hand pose tracking. [PDF]

Kha Gia Quach, Chi Nhan Duong, Khoa Luu, and Tien D. Bui.

[2016 IJCAI] Model-based Deep Hand Pose Estimation. [PDF] [Project Page] [Code]

Xingyi Zhou, Qingfu Wan, Wei Zhang, Xiangyang Xue, Yichen Wei

[2016 SIGGRAPH] Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences. [PDF]

Jonathan Taylor et al.

[2016 SIGGRAPH Asia] Sphere-Meshes for Real-Time Hand Modeling and Tracking. [PDF]  [Project Page] [Code]

Anastasia Tkach, Mark Pauly, Andrea Tagliasacchi

2016 CVPR

Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs. [PDF] [Project Page] [Code]

Liuhao Ge, Hui Liang, Junsong Yuan, Daniel Thalmann

DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features.  [PDF][Project Page]

Ayan Sinha*, Chiho Choi*, Karthik Ramani

Efficiently Creating 3D Training Data for Fine Hand Pose Estimation. [PDF] [Project Page] [Code]

Markus Oberweger, Gernot Riegler, Paul Wohlhart, Vincent Lepetit

Fits Like a Glove: Rapid and Reliable Hand Shape Personalization.  [PDF] [Project Page]

David Joseph Tan, Thomas Cashman, Jonathan Taylor, Andrew Fitzgibbon, Daniel Tarlow, Sameh Khamis, Shahram Izadi, Jamie Shotton

2015 ICCV

Training a Feedback Loop for Hand Pose Estimation. [PDF] [Project Page]

Markus Oberweger, Paul Wohlhart, Vincent Lepetit

Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose.  [PDF]

Danhang Tang, Jonathan Taylor, Pushmeet Kohli, Cem Keskin, Tae-Kyun Kim, Jamie Shotton

Depth-based hand pose estimation: data, methods, and challenges. [PDF] [Project Page] [Code]

James Supancic III, Deva Ramanan, Gregory Rogez, Yi Yang, Jamie Shotton

3D Hand Pose Estimation Using Randomized Decision Forest with Segmentation Index Points. [PDF]

Peiyi Li, Haibin Ling

A collaborative filtering approach to real-time hand pose estimation. [PDF] [Project Page]

Chiho Choi, Ayan Sinha, Joon Hee Choi, Sujin Jang, Karthik Ramani

Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions. [PDF]

Sven Bambach, Stefan Lee, David Crandall, Chen Yu

Understanding Everyday Hands in Action from RGB-D Images. [PDF]

Gregory Rogez, James Supancic III, Deva Ramanan

2015 CVPR

Cascaded Hand Pose Regression.  [PDF]

Xiao Sun, Yichen Wei, Shuang Liang, Xiaoou Tang, and Jian Sun

Fast and Robust Hand Tracking Using Detection-Guided Optimization. [PDF] [Project Page]

Srinath Sridhar, Franziska Mueller, Antti Oulasvirta, Christian Theobalt

Learning an Efficient Model of Hand Shape Variation from Depth Images. [PDF]

Sameh Khamis, Jonathan Taylor, Jamie Shotton, Cem Keskin, Shahram Izadi, Andrew Fitzgibbon

2015 Others

[2015 BMVC] Rule of Thumb: Deep Derotation for Improved Fingertip Detection. [PDF] [Project Page]

Aaron Wetzler, Ron Slossberg and Ron Kimmel

[2015 CHI] Accurate, Robust, and Flexible Real-time Hand Tracking. [PDF] [Project Page]

Toby Sharp, Cem Keskin, Duncan Robertson, Jonathan Taylor, Jamie Shotton, David Kim, Christoph Rhemann, Ido Leichter, Alon Vinnikov, Yichen Wei, Daniel Freedman, Pushmeet Kohli, Eyal Krupka, Andrew Fitzgibbon, Shahram Izadi

[2015 CVWW]Hands Deep in Deep Learning for Hand Pose Estimation. [PDF] [Project Page] [Code]

Markus Oberweger, Paul Wohlhart, Vincent Lepetit

[2015 FG]Combining Discriminative and Model Based Approaches for Hand Pose Estimation. [PDF] [Project Page]

Philip Krejov, Andrew Gilbert, Richard Bowden

[2015 SGP] Robust Articulated-ICP for Real-Time Hand Tracking. [PDF]  [Project Page] [Code]

Anastasia Tkach, Mark Pauly, Andrea Tagliasacchi

2014 CVPR

Realtime and robust hand tracking from depth. [PDF] [Project Page]

Chen Qian, Xiao Sun, Yichen Wei, Xiaoou Tang and Jian Sun

Latent regression forest: Structured estimation of 3d articulated hand posture. [PDF] [Project Page]

Danhang Tang, Hyung Jin Chang, Alykhan Tejani, T-K. Kim

User-specific hand modeling from monocular depth sequences. [PDF] [Project Page]

Jonathan Taylor, Richard Stebbing, Varun Ramakrishna, Cem Keskin, Jamie Shotton, Shahram Izadi, Aaron Hertzmann, Andrew Fitzgibbon

Evolutionary Quasi-random Search for Hand Articulations Tracking. [PDF] [Project Page]

Iason Oikonomidis, Manolis IA Lourakis, Antonis A Argyros

2014 Others & Before

[2014 SIGGRAPH] Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks. [PDF] [Project Page]

Jonathan Tompson, Murphy Stein, Yann Lecun and Ken Perlin

[2013 ICCV] Real-time Articulated Hand Pose Estimation using Semi-supervised Transductive Regression Forests. [PDF] [Project Page]

Danhang Tang, Tsz Ho Yu and T-K. Kim

[2013 ICCV] Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data. [PDF] [Project Page]

Srinath Sridhar, Antti Oulasvirta, Christian Theobalt

[2013 ICCV] Efficient Hand Pose Estimation from a Single Depth Image. [PDF] [Project Page]

Chi Xu, Li Cheng

[2012 ECCV] Motion Capture of Hands in Action using Discriminative Salient Points. [PDF] [Project Page]

Ballan, L. and Taneja, A. and Gall, J. and van Gool, L. and Pollefeys, M.

[2012 ECCV] Hand pose estimation and hand shape classification using multi-layered randomized decision forests.

Cem KeskinFurkan, K?ra?Yunus Emre, KaraLale Akarun

[2011 CVPRW] Real Time Hand Pose Estimation using Depth Sensors. [PDF]

Cem Keskin, Furkan K?rac, Yunus Emre Kara, Lale Akarun

[2011 BMVC] Efficient Model-based 3D Tracking of Hand Articulations using Kinect. [PDF] [Project Page] [Code]

Iason Oikonomidis, Nikolaos Kyriazis, Antonis A. Argyros

Journal Papers

[2017 CVIU] Hand Pose Estimation through Semi-Supervised and Weakly-Supervised Learning. [PDF]

Natalia Neverova, Christian Wolf, Florian Nebout, Graham Taylor

[2016 IJCV] Capturing Hands in Action using Discriminative Salient Points and Physics Simulation. [PDF] [Project Page]

Tzionas, D., Ballan, L., Srikantha, A., Aponte, P., Pollefeys, M., Gall, J.

[2016 IJCV] Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups. [PDF] [Project Page]

Chi Xu, Lakshmi Narasimhan Govindarajan, Yu Zhang, Li Cheng

[2016 TPAMI] Latent Regression Forest: Structured Estimation of 3D Hand Poses. [PDF]

Danhang Tang, Hyung Chang, Alykhan Tejani, Tae-Kyun Kim

[2016 CVIU] Guided Optimisation through Classification and Regression for Hand Pose Estimation. [PDF] [Project Page]

Philip Krejov, Andrew Gilbert, Richard Bowden

[2015 TCSVT] Resolving Ambiguous Hand Pose Predictions by Exploiting Part Correlations. [PDF]

Hui Liang, Junsong Yuan, Daniel Thalmann

[2015 IJCV] Estimate Hand Poses Efficiently from Single Depth Images. [PDF] [Project Page]  [Code]

Chi Xu, Ashwin Nanjappa, Xiaowei Zhang, Li Cheng

[2014 TMM] Parsing the Hand in Depth Images. [PDF] [Project Page]  [Code]

Hui Liang, Junsong Yuan, Daniel Thalmann

Theses

[2017 Thesis] Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects. [PDF] [Project Page]

Dimitrios Tzionas, University of Bonn

[2016 Thesis] Tracking Hands in Action for Gesture-based Computer Input. [PDF]

Srinath Sridhar,  Max Planck Institute for Informatics

[2016 Thesis] 3D hand pose regression with variants of decision forests. [PDF] [Project Page]

Danhang Tang, Imperial College London

[2016 Thesis] Deep Learning for Human Motion Analysis. [PDF] [Project Page]

Natalia Neverova, National Institut of Applied Science (INSA de Lyon), France

[2016 Thesis] Real time hand pose estimation for human computer interaction. [PDF] [Project Page]

Philip Krejov, University of Surrey

[2015 Thesis] Efficient Tracking of the 3D Articulated Motion of Human Hands. [PDF]

Iason Oikonomidis, University of Crete

[2015 Thesis] Vision-based hand pose estimation and gesture recognition. [PDF]

Hui Liang, Nanyang Technological University

[2015 Thesis] Localization of Humans in Images Using Convolutional Networks. [PDF]

Jonathan Tompson, New York University

Datasets

NYU Hand Pose Dataset
ICVL Dataset
MARA15 Dataset
BigHand2.2M Benchmark
  • Website
  • Related Paper: Big Hand 2.2M Benchmark: Hand Pose Data Set and State of the Art Analysis, CVPR 2017 [PDF]
MARC (FingerPaint) Dataset
UCI-EGO Dataset
Hands in Action Dataset
HandNet Dataset (Fingertip)
MARA14 Dataset
Dexter 1 Dataset
ASTAR Dataset

Credits:

  • [1] Big Hand 2.2M Benchmark: Hand Pose Data Set and State of the Art Analysis, CVPR 2017 [PDF]
  • [2] http://arrummzen.net/#HandData
  • [3] Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects. [PDF]

Challenges

The 2017 Hands in the Million Challenge on 3D Hand Pose Estimation.

3rd International Workshop on Observing and Understanding Hands in Action ( HANDS 2017), ICCV 2017

Other Related Papers

[2017 ICCV] Low-Dimensionality Calibration through Local Anisotropic Scaling for Robust Hand Model Personalization. [PDF]  [Project Page] [Code]

Edoardo Remelli*, Anastasia Tkach*, Andrea Tagliasacchi, Mark Pauly

[2017 Neurocomputing] Multi-task, Multi-domain Learning: application to semantic segmentation and pose regression.

Fourure, Damien, et al.

[arXiv:1704.02463] First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations. [PDF]

Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek, Tae-Kyun Kim

[2017 CVPR] SurfNet: Generating 3D shape surfaces using deep residual networks. [PDF]

Ayan Sinha, Asim Unmesh, Qixing Huang, Karthik Ramani

[2017 CVPR] Learning from Simulated and Unsupervised Images through Adversarial Training. [PDF] [Project Page] [Code-Tensorflow] [Code-Keras] [Code-Tensorflow-NYU-Hand]

Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb

[2016 3DV] Learning to Navigate the Energy Landscape. [PDF] [Project Page]

Julien Valentin, Angela Dai, Matthias Niessner, Pushmeet Kohli, Philip H.S. Torr, Shahram Izadi

[2016 NIPS] DISCO Nets : Dissimilarity Coefficient Networks. [PDF] [Project Page] [Code]

Diane Bouchacourt, M. Pawan Kumar, Sebastian Nowozin

[2015 ICCV] 3D Object Reconstruction from Hand-Object Interactions. [PDF] [Project Page]

Dimitrios Tzionas and Juergen Gall

all * .files come from : https://github.com/xinghaochen/awesome-hand-pose-estimation#2017-iccv

时间： 2024-11-06 20:20:43

paper 154：姿态估计（Hand Pose Estimation）相关总结的相关文章

相机姿态估计（Pose Estimation）

根据相机成像原理我们知道相机成像平面的投影点像素坐标 $p=KP$.其中K是相机内参数矩阵,P是空间点的3D坐标,p和P都是齐次坐标,该等式在齐次意义下成立(即乘任意常数都成立). 于是对于两个相机各自的坐标系,有:$$p_0=KP,p_1=K(RP+t)$$ 其中R为旋转矩阵(Rotation),t为平移向量(Translation).令$x = K^{-1}p$,去掉内参K归一化成: $$x_0=P, x_1=RP+t$$ 由这两式得:$$x_1 = Rx_0+t$$

human pose estimation

2D Pose estimation主要面临的困难:遮挡.复杂背景.光照.真实世界的复杂姿态.人的尺度不一.拍摄角度不固定等. 单人姿态估计 传统方法:基于Pictorial Structures, DPM ? 基于深度学习的算法包括直接回归坐标(Deep Pose)和通过热力图回归坐标(CPM, Hourlgass) 目前单人姿态估计,主流算法是基于Hourlgass各种更改结构的算法. 多人姿态估计 二维图像姿态估计基于CNN的多人姿态估计方法,通常有2个思路(Bottom-Up Appro

在自遮挡下的单目图像3D姿态估计 Monocular Image 3D Human Pose Estimation under Self-Occlusion (ICCV 13)

Monocular Image 3D Human Pose Estimationunder Self-Occlusion (ICCV 13) 在自遮挡下的单目图像3D姿态估计 摘要:文中提出在单张图片中3D姿态自动重建的方法.人体关节.易产生幻觉的身体部位的存在,杂乱的背景,都将导致人体姿态判断的歧义性,这都说明这不是一个简单的问题.研究者研究了许多基于运动和阴影的方法,为了减小歧义性,并对3D姿态进行重建.我们算法的关键思想就是增加运动和方向限制.前一个是在3D模型映射到输入图像时增加的限制,

6D姿态估计从0单排——看论文的小鸡篇——Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes

这是linemod的第二篇,这一篇把训练从online learning 变成了 使用3D model, 并且对于检测结果用 3种方法: color.Pose.Depth来确保不会有false positive.感觉有种不忘初心的感觉(笑 基于linemod,是前一篇的改良 initial version of LINEMOD has some disadvantages. First, templates are learnede online, which is difficule to c

3D目标检测&6D姿态估计之SSD-6D算法--by leona

最近的研究主要以6D检测为主,本篇介绍基于2D检测器SSD的3D检测器SSD-6D. 1)论文链接:https://arxiv.org/pdf/1711.10006.pdf   训练部分代码链接:https://github.com/wadimkehl/ssd-6d 2)介绍: 许多3D检测器都是基于视角的(view based),生成一系列离散的目标视角用于后续视频序列的特征计算.在测试过程中,从不同的离散视角对场景进行采样,然后计算特征,并与目标数据库匹配来建立训练视角和场景位置的对应.此处

caffe openpose/Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields配置（转）

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields 是CVPR2017的一篇论文,作者称是世界上第一个基于深度学习的实时多人二维姿态估计. 优酷演示地址:链接 前几天作者公布了windows下的代码,下面来说说如何配置: 英文配置地址可以参考作者的github:https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/inst

caffe openpose/Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields配置(转)

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields 是CVPR2017的一篇论文,作者称是世界上第一个基于深度学习的实时多人二维姿态估计. 优酷演示地址:链接 前几天作者公布了windows下的代码,下面来说说如何配置: 英文配置地址可以参考作者的github:https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/inst

Facebook提出DensePose数据集和网络架构：可实现实时的人体姿态估计

https://baijiahao.baidu.com/s?id=1591987712899539583 选自arXiv 作者:Rza Alp Güler, Natalia Neverova, Iasonas Kokkinos 机器之心编译 参与:Panda 实现从 2D 图像到 3D 表面的对应在很多方面都有极具价值的应用前景.近日,FAIR 发布了一篇研究论文,介绍了他们通过人工方式标注的图像到表面密集对应数据集 DensePose-COCO 以及基于此训练的 DensePose-RCNN

POSIT算法的原理--opencv 3D姿态估计

3D姿态估计-POSIT算法 POSIT算法,Pose from Orthography and Scaling with Iterations, 比例正交投影迭代变换算法: 用于估计物体的3D姿态(相对于镜头的平移和旋转量).算法正常工作的前提是物体在Z轴方向的"厚度"远小于其在Z轴方向的平均深度,比如距离镜头10米远的一张椅子. 算法流程: 假设待求的姿态,包括旋转矩阵R和平移向量T,分别为 透视投影变换为: 上式中的f是摄像机的焦距,它的具体值并不重要,重要的是f与x和y之间的比