scholarly journals Multi-View Pose Generator Based on Deep Learning for Monocular 3D Human Pose Estimation

Symmetry ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1116 ◽  
Author(s):  
Jun Sun ◽  
Mantao Wang ◽  
Xin Zhao ◽  
Dejun Zhang
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Data Augmentation ◽  
Estimation Method ◽  
Human Pose Estimation ◽  
Convolutional Network ◽  
3D Pose Estimation ◽  
Single View ◽  
Human Pose ◽  
3D Human Pose Estimation

In this paper, we study the problem of monocular 3D human pose estimation based on deep learning. Due to single view limitations, the monocular human pose estimation cannot avoid the inherent occlusion problem. The common methods use the multi-view based 3D pose estimation method to solve this problem. However, single-view images cannot be used directly in multi-view methods, which greatly limits practical applications. To address the above-mentioned issues, we propose a novel end-to-end 3D pose estimation network for monocular 3D human pose estimation. First, we propose a multi-view pose generator to predict multi-view 2D poses from the 2D poses in a single view. Secondly, we propose a simple but effective data augmentation method for generating multi-view 2D pose annotations, on account of the existing datasets (e.g., Human3.6M, etc.) not containing a large number of 2D pose annotations in different views. Thirdly, we employ graph convolutional network to infer a 3D pose from multi-view 2D poses. From experiments conducted on public datasets, the results have verified the effectiveness of our method. Furthermore, the ablation studies show that our method improved the performance of existing 3D pose estimation networks.

scholarly journals A Baseline for Cross-Database 3D Human Pose Estimation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3769
Author(s):  
Michał Rapczyński ◽  
Philipp Werner ◽  
Sebastian Handrich ◽  
Ayoub Al-Hamadi
Keyword(s):  
Pose Estimation ◽  
Real Life ◽  
Human Pose Estimation ◽  
3D Pose Estimation ◽  
Multiple Datasets ◽  
In The Wild ◽  
Scale Normalization ◽  
Human Pose ◽  
Future Work ◽  
3D Human Pose Estimation

Vision-based 3D human pose estimation approaches are typically evaluated on datasets that are limited in diversity regarding many factors, e.g., subjects, poses, cameras, and lighting. However, for real-life applications, it would be desirable to create systems that work under arbitrary conditions (“in-the-wild”). To advance towards this goal, we investigated the commonly used datasets HumanEva-I, Human3.6M, and Panoptic Studio, discussed their biases (that is, their limitations in diversity), and illustrated them in cross-database experiments (for which we used a surrogate for roughly estimating in-the-wild performance). For this purpose, we first harmonized the differing skeleton joint definitions of the datasets, reducing the biases and systematic test errors in cross-database experiments. We further proposed a scale normalization method that significantly improved generalization across camera viewpoints, subjects, and datasets. In additional experiments, we investigated the effect of using more or less cameras, training with multiple datasets, applying a proposed anatomy-based pose validation step, and using OpenPose as the basis for the 3D pose estimation. The experimental results showed the usefulness of the joint harmonization, of the scale normalization, and of augmenting virtual cameras to significantly improve cross-database and in-database generalization. At the same time, the experiments showed that there were dataset biases that could not be compensated and call for new datasets covering more diversity. We discussed our results and promising directions for future work.

scholarly journals 3D Single Person Pose Estimation Method Based on Deep Learning

2020 ◽  
Author(s):  
Xinrui Yuan ◽  
Hairong Wang ◽  
Jun Wang
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Estimation Method ◽  
Hybrid Network ◽  
Estimation Methods ◽  
Human Pose Estimation ◽  
Single Person ◽  
Depth Study ◽  
Human Pose ◽  
Set Up

In view of the significant effects of deep learning in graphics and image processing, research on human pose estimation methods using deep learning has attracted much attention, and many method models have been produced one after another. On the basis of tracking and in-depth study of domestic and foreign research results, this paper concentrates on 3D single person pose estimation methods, contrasts and analyzes three methods of end-to-end, staged and hybrid network models, and summarizes the characteristics of the methods. For evaluating method performance, set up an experimental environment, and utilize the Human3.6M data set to test several mainstream methods. The test results indicate that the hybrid network model method has a better performance in the field of human pose estimation.

scholarly journals Deep Learning Methods for 3D Human Pose Estimation under Different Supervision Paradigms: A Survey

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2267
Author(s):  
Dejun Zhang ◽  
Yiqi Wu ◽  
Mingyue Guo ◽  
Yilin Chen
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Literature Survey ◽  
Estimation Methods ◽  
Human Pose Estimation ◽  
Extensive Literature ◽  
Learning Methods ◽  
Human Pose ◽  
3D Human Pose Estimation ◽  
Research Studies

The rise of deep learning technology has broadly promoted the practical application of artificial intelligence in production and daily life. In computer vision, many human-centered applications, such as video surveillance, human-computer interaction, digital entertainment, etc., rely heavily on accurate and efficient human pose estimation techniques. Inspired by the remarkable achievements in learning-based 2D human pose estimation, numerous research studies are devoted to the topic of 3D human pose estimation via deep learning methods. Against this backdrop, this paper provides an extensive literature survey of recent literature about deep learning methods for 3D human pose estimation to display the development process of these research studies, track the latest research trends, and analyze the characteristics of devised types of methods. The literature is reviewed, along with the general pipeline of 3D human pose estimation, which consists of human body modeling, learning-based pose estimation, and regularization for refinement. Different from existing reviews of the same topic, this paper focus on deep learning-based methods. The learning-based pose estimation is discussed from two categories: single-person and multi-person. Each one is further categorized by data type to the image-based methods and the video-based methods. Moreover, due to the significance of data for learning-based methods, this paper surveys the 3D human pose estimation methods according to the taxonomy of supervision form. At last, this paper also enlists the current and widely used datasets and compares performances of reviewed methods. Based on this literature survey, it can be concluded that each branch of 3D human pose estimation starts with fully-supervised methods, and there is still much room for multi-person pose estimation based on other supervision methods from both image and video. Besides the significant development of 3D human pose estimation via deep learning, the inherent ambiguity and occlusion problems remain challenging issues that need to be better addressed.

scholarly journals Sequential 3D Human Pose Estimation Using Adaptive Point Cloud Sampling Strategy

2021 ◽  
Author(s):  
Zihao Zhang ◽  
Lei Hu ◽  
Xiaoming Deng ◽  
Shihong Xia
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Fundamental Problem ◽  
Estimation Method ◽  
Sampling Strategy ◽  
Point Clouds ◽  
Human Pose Estimation ◽  
Human Pose ◽  
New Perspective ◽  
3D Human Pose Estimation

3D human pose estimation is a fundamental problem in artificial intelligence, and it has wide applications in AR/VR, HCI and robotics. However, human pose estimation from point clouds still suffers from noisy points and estimated jittery artifacts because of handcrafted-based point cloud sampling and single-frame-based estimation strategies. In this paper, we present a new perspective on the 3D human pose estimation method from point cloud sequences. To sample effective point clouds from input, we design a differentiable point cloud sampling method built on density-guided attention mechanism. To avoid the jitter caused by previous 3D human pose estimation problems, we adopt temporal information to obtain more stable results. Experiments on the ITOP dataset and the NTU-RGBD dataset demonstrate that all of our contributed components are effective, and our method can achieve state-of-the-art performance.

Sign in / Sign up

Export Citation Format

Share Document