人体姿态估计资源大列表(Human Pose Estimation)

2018 年 10 月 6 日 专知
人体姿态估计资源大列表(Human Pose Estimation)

【导读】给定一幅图像或一段视频,人体姿态识别就是去恢复其中人体关节点位置的过程。这篇推送总结了近几年来人体姿态估计的论文列表~ 欢迎查看!


基础:

  • Human Pose Estimation 101 

https://github.com/cbsudux/Human-Pose-Estimation-101


论文:

2D姿态估计

  • Learning Human Pose Estimation Features with Convolutional Networks - Jain, A., Tompson, J., Andriluka, M., Taylor, G.W., & Bregler, C. (ICLR 2013)

  • DeepPose: Human Pose Estimation via Deep Neural Networks - Toshev, A., & Szegedy, C. (CVPR 2014)

  • Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation - [CODE] - Tompson, J., Jain, A., LeCun, Y., & Bregler, C. (NIPS 2014)

  • MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation - Jain, A., Tompson, J., LeCun, Y., & Bregler, C. (ACCV 2014)

  • Efficient Object Localization Using Convolutional Networks - Tompson, J., Goroshin, R., Jain, A., LeCun, Y., & Bregler, C (CVPR 2015)

  • Flowing ConvNets for Human Pose Estimation in Videos - [CODE] - Pfister, T., Charles, J., & Zisserman, A. (ICCV 2015)

  • Convolutional Pose Machines - [CODE] - Wei, S., Ramakrishna, V., Kanade, T., & Sheikh, Y. (CVPR 2016)

  • Human Pose Estimation with Iterative Error Feedback[CODE] Carreira, J., Agrawal, P., Fragkiadaki, K., & Malik, J. (CVPR 2016)

  • DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation - [CODE] - Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P.V., & Schiele, B. (CVPR 2016)

  • DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model - [CODE1][CODE2] - Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., & Schiele, B. (ECCV 2016)

  • Stacked Hourglass Networks for Human Pose Estimation - [CODE] - Newell, A., Yang, K., & Deng, J. (ECCV 2016)

  • Multi-context Attention for Human Pose Estimation - [CODE] - Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., & Wang, X. (CVPR 2017)

  • Towards Accurate Multi-person Pose Estimation in the Wild - [CODE] - Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., & Murphy, K.P. (CVPR 2017)

  • Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields - [CODE] - Cao, Z., Simon, T., Wei, S., & Sheikh, Y. (CVPR 2017)

  • Learning Feature Pyramids for Human Pose Estimation - [CODE] - Yang, W., Li, S., Ouyang, W., Li, H., & Wang, X. (ICCV 2017)

  • Human Pose Estimation Using Global and Local Normalization - Sun, K., Lan, C., Xing, J., Zeng, W., Liu, D., & Wang, J. (ICCV 2017)

  • Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation - Chen, Y., Shen, C., Wei, X., Liu, L., & Yang, J. (ICCV 2017)

  • RMPE: Regional Multi-person Pose Estimation - [CODE1][CODE2] - Fang, H., Xie, S., & Lu, C. (ICCV 2017)

  • Self Adversarial Training for Human Pose Estimation - [CODE1][CODE2] - Chou, C., Chien, J., & Chen, H. (ArXiv 2017)

  • Recurrent Human Pose Estimation - [CODE] - Belagiannis, V., & Zisserman, A. (FG 2017)

  • Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation - [CODE] Ning, G., Zhang, Z., & He, Z. (IEEE Transactions on Multimedia 2018)

  • Human Pose Estimation with Parsing Induced Learner- Xuecheng Nie, Jiashi Feng, Yiming Zuo, Shuicheng Yan (CVPR 2018)

  • LSTM Pose Machines - [CODE] - Yue Luo, Jimmy Ren, Zhouxia Wang, Wenxiu Sun, Jinshan Pan, Jianbo Liu, Jiahao Pang, Liang Lin (CVPR 2018)

3D姿态估计

  • 3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network - Li, S., & Chan, A.B. (ACCV 2014)

  • Structured Prediction of 3D Human Pose with Deep Neural Networks - Tekin, B., Katircioglu, I., Salzmann, M., Lepetit, V., & Fua, P. (BMVC 2016)

  • VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera - [CODE] - Mehta, Dushyant et al. (SIGGRAPH 2017)

  • Recurrent 3D Pose Sequence Machines - Lin, M., Lin, L., Liang, X., Wang, K., & Cheng, H. (CVPR 2017)

  • Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image - Tomè, D., Russell, C., & Agapito, L. (CVPR 2017)

  • Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose - [CODE] - Pavlakos, G., Zhou, X., Derpanis, K.G., & Daniilidis, K. (CVPR 2017)

  • Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach - [CODE] - Zhou, X., Huang, Q., Sun, X., Xue, X., & Wei, Y. (ICCV 2017)

  • A Simple Yet Effective Baseline for 3d Human Pose Estimation - Martinez, J., Hossain, R., Romero, J., & Little, J.J. (ICCV 2017)

  • Compositional Human Pose Regression - Sun, X., Shang, J., Liang, S., & Wei, Y. (ICCV 2017)

  • Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision - Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., & Theobalt, C. (3DV 2017)

  • 3D Human Pose Estimation in the Wild by Adversarial Learning - Yang, W., Ouyang, W., Wang, X., Ren, J.S., Li, H., & Wang, X. (2018)

  • End-to-end Recovery of Human Shape and Pose - [CODE] - Kanazawa, A., Black, M.J., Jacobs, D.W., & Malik, J. (CVPR 2018)

  • Learning to Estimate 3D Human Pose and Shape from a Single Color Image - Pavlakos, G., Zhu, L., Zhou, X., & Daniilidis, K. (CVPR 2018)

  • Dense Human Pose Estimation In The Wild - [CODE] - Guler, R.A., Neverova, N., & Kokkinos, I. (ArXiv 2018)

  • Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation - [CODE] - Omran, Mohamed and Lassner, Christoph and Pons-Moll, Gerard and Gehler, Peter V. and Schiele, Bernt (3DV 2018)

  • Learning 3D Human Pose from Structure and Motion - Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., & Jain, A. (ECCV 2018)

  • Integral Human Pose Regression - [CODE] - Sun, X., Xiao, B., Liang, S., & Wei, Y. (ECCV 2018)

  • Dense Pose Transfer - Neverova, N., Guler, R.A., & Kokkinos, I. (ECCV 2018)

  • Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation - [CODE] - Rhodin, H., Salzmann, M., & Fua, P. (ECCV 2018)

  • BodyNet: Volumetric Inference of 3D Human Body Shapes - [CODE] - Varol, G., Ceylan, D., Russell, B., Yang, J., Yumer, E., Laptev, I., & Schmid, C. (ECCV 2018)

人物生成

  • Pose Guided Person Image Generation - [CODE] - Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., & Gool, L.V. (NIPS 2017)

  • A Generative Model of People in Clothing - Lassner, C., Pons-Moll, G., & Gehler, P.V. (ICCV 2017)

  • Deformable GANs for Pose-based Human Image Generation - [CODE] - Siarohin, A., Sangineto, E., Lathuilière, S., & Sebe, N. (CVPR 2018)

  • Dense Pose Transfer - Neverova, N., Guler, R.A., & Kokkinos, I. (ECCV 2018)

实时姿态估计

  • Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields - [CODE] - Cao, Z., Simon, T., Wei, S., & Sheikh, Y. (CVPR 2017)

  • VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera - [CODE] - Mehta, Dushyant et al. (SIGGRAPH 2017)

  • RMPE: Regional Multi-person Pose Estimation - [CODE1][CODE2] - Fang, H., Xie, S., & Lu, C. (ICCV 2017)

  • Dense Human Pose Estimation In The Wild - [CODE] - Guler, R.A., Neverova, N., & Kokkinos, I. (ArXiv 2018)


数据集

2D

  • MPII Human Pose Dataset 

  • LSP

  • FLIC

  • FLIC-plus


3D

  • Human3.6M

  • HumanEva

  • MPI-INF-3DHP

  • Unite The People


Github地址:

https://github.com/cbsudux/awesome-human-pose-estimation

-END-

专 · 知


人工智能领域26个主题知识资料全集获取与加入专知人工智能服务群: 欢迎微信扫一扫加入专知人工智能知识星球群,获取专业知识教程视频资料和与专家交流咨询!


请PC登录www.zhuanzhi.ai或者点击阅读原文,注册登录专知,获取更多AI知识资料!


请加专知小助手微信(扫一扫如下二维码添加),加入专知主题群(请备注主题类型:AI、NLP、CV、 KG等)交流~

 AI 项目技术 & 商务合作:bd@zhuanzhi.ai, 或扫描上面二维码联系!

请关注专知公众号,获取人工智能的专业知识!

点击“阅读原文”,使用专知

登录查看更多
8

相关内容

CVPR是IEEE Conference on Computer Vision and Pattern Recognition的缩写,即IEEE国际计算机视觉与模式识别会议。该会议是由IEEE举办的计算机视觉和模式识别领域的顶级会议。

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等

Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving vehicle. The accuracy of human keypoint prediction is increasingly improved thanks to the burgeoning development of deep learning. Most existing methods solved human pose estimation by generating heatmaps in which the ith heatmap indicates the location confidence of the ith keypoint. In this paper, we introduce novel network structures referred to as multiresolution representation learning for human keypoint prediction. At different resolutions in the learning process, our networks branch off and use extra layers to learn heatmap generation. We firstly consider the architectures for generating the multiresolution heatmaps after obtaining the lowest-resolution feature maps. Our second approach allows learning during the process of feature extraction in which the heatmaps are generated at each resolution of the feature extractor. The first and second approaches are referred to as multi-resolution heatmap learning and multi-resolution feature map learning respectively. Our architectures are simple yet effective, achieving good performance. We conducted experiments on two common benchmarks for human pose estimation: MS-COCO and MPII dataset.

0
5
下载
预览

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at \url{https://github.com/leoxiaobin/deep-high-resolution-net.pytorch}.

0
5
下载
预览

Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different transformations of the input image on the segmentation output. Test-time augmentation has been previously used to improve segmentation accuracy, yet not been formulated in a consistent mathematical framework. Hence, we also propose a theoretical formulation of test-time augmentation, where a distribution of the prediction is estimated by Monte Carlo simulation with prior distributions of parameters in an image acquisition model that involves image transformations and noise. We compare and combine our proposed aleatoric uncertainty with model uncertainty. Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images (MRI) showed that 1) the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating the test-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions, and 2) our test-time augmentation outperforms a single-prediction baseline and dropout-based multiple predictions.

0
7
下载
预览

Estimating the head pose of a person is a crucial problem that has a large amount of applications such as aiding in gaze estimation, modeling attention, fitting 3D models to video and performing face alignment. Traditionally head pose is computed by estimating some keypoints from the target face and solving the 2D to 3D correspondence problem with a mean human head model. We argue that this is a fragile method because it relies entirely on landmark detection performance, the extraneous head model and an ad-hoc fitting step. We present an elegant and robust way to determine pose by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles (yaw, pitch and roll) directly from image intensities through joint binned pose classification and regression. We present empirical tests on common in-the-wild pose benchmark datasets which show state-of-the-art results. Additionally we test our method on a dataset usually used for pose estimation using depth and start to close the gap with state-of-the-art depth pose methods. We open-source our training and testing code as well as release our pre-trained models.

0
5
下载
预览

We propose a scalable, efficient and accurate approach to retrieve 3D models for objects in the wild. Our contribution is twofold. We first present a 3D pose estimation approach for object categories which significantly outperforms the state-of-the-art on Pascal3D+. Second, we use the estimated pose as a prior to retrieve 3D models which accurately represent the geometry of objects in RGB images. For this purpose, we render depth images from 3D models under our predicted pose and match learned image descriptors of RGB images against those of rendered depth images using a CNN-based multi-view metric learning approach. In this way, we are the first to report quantitative results for 3D model retrieval on Pascal3D+, where our method chooses the same models as human annotators for 50% of the validation images on average. In addition, we show that our method, which was trained purely on Pascal3D+, retrieves rich and accurate 3D models from ShapeNet given RGB images of objects in the wild.

0
7
下载
预览

This study considers the 3D human pose estimation problem in a single RGB image by proposing a conditional random field (CRF) model over 2D poses, in which the 3D pose is obtained as a byproduct of the inference process. The unary term of the proposed CRF model is defined based on a powerful heat-map regression network, which has been proposed for 2D human pose estimation. This study also presents a regression network for lifting the 2D pose to 3D pose and proposes the prior term based on the consistency between the estimated 3D pose and the 2D pose. To obtain the approximate solution of the proposed CRF model, the N-best strategy is adopted. The proposed inference algorithm can be viewed as sequential processes of bottom-up generation of 2D and 3D pose proposals from the input 2D image based on deep networks and top-down verification of such proposals by checking their consistencies. To evaluate the proposed method, we use two large-scale datasets: Human3.6M and HumanEva. Experimental results show that the proposed method achieves the state-of-the-art 3D human pose estimation performance.

0
3
下载
预览

The task of multi-person human pose estimation in natural scenes is quite challenging. Existing methods include both top-down and bottom-up approaches. The main advantage of bottom-up methods is its excellent tradeoff between estimation accuracy and computational cost. We follow this path and aim to design smaller, faster, and more accurate neural networks for the regression of keypoints and limb association vectors. These two regression tasks are naturally dependent on each other. In this work, we propose a dual-path network specially designed for multi-person human pose estimation, and compare our performance with the openpose network in aspects of model size, forward speed, and estimation accuracy.

0
3
下载
预览
小贴士
相关VIP内容
专知会员服务
44+阅读 · 2020年3月19日
专知会员服务
99+阅读 · 2020年3月12日
AAAI2020接受论文列表,1591篇论文目录全集
专知会员服务
89+阅读 · 2020年1月12日
专知会员服务
26+阅读 · 2020年1月10日
【深度学习视频分析/多模态学习资源大列表】
专知会员服务
61+阅读 · 2019年10月16日
计算机视觉最佳实践、代码示例和相关文档
专知会员服务
9+阅读 · 2019年10月9日
机器学习相关资源(框架、库、软件)大列表
专知会员服务
24+阅读 · 2019年10月9日
相关论文
Simple Multi-Resolution Representation Learning for Human Pose Estimation
Trung Q. Tran,Giang V. Nguyen,Daeyoung Kim
5+阅读 · 2020年4月14日
Chaoxu Guo,Bin Fan,Jie Gu,Qian Zhang,Shiming Xiang,Veronique Prinet,Chunhong Pan
4+阅读 · 2019年3月21日
Ke Sun,Bin Xiao,Dong Liu,Jingdong Wang
5+阅读 · 2019年2月25日
Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
Guotai Wang,Wenqi Li,Michael Aertsen,Jan Deprest,Sebastien Ourselin,Tom Vercauteren
7+阅读 · 2018年7月20日
Test-time augmentation with uncertainty estimation for deep learning-based medical image segmentation
Guotai Wang,Wenqi Li,Michael Aertsen,Jan Deprest,Sebastien Ourselin,Tom Vercauteren
3+阅读 · 2018年7月19日
Nataniel Ruiz,Eunji Chong,James M. Rehg
5+阅读 · 2018年4月13日
Alexander Grabner,Peter M. Roth,Vincent Lepetit
7+阅读 · 2018年3月30日
Ju Yong Chang,Kyoung Mu Lee
3+阅读 · 2017年12月28日
Rohit Girdhar,Georgia Gkioxari,Lorenzo Torresani,Manohar Paluri,Du Tran
7+阅读 · 2017年12月26日
Guanghan Ning,Zhihai He
3+阅读 · 2017年10月27日
Top