Deep Kinematics Analysis for Monocular 3D Human Pose Estimation

Xu, Jingwei; Yu, Zhenbo; Ni, Bingbing; Yang, Jiancheng; Yang, Xiaokang; Zhang, Wenjun

doi:10.1109/cvpr42600.2020.00098

Cited by 163 publications

(54 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many recent works [9,20,27,35,42,46] propose novel reparameterization methods for 3D human poses at the output end. Sun et al [35] use bones instead of joints to represent human poses, and exploit the joint connection structure to define a compositional loss function for training.…”

Section: Positional Informationmentioning

confidence: 99%

Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation

Wenkang

Wang

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints (local motion) instead of the overall trajectory of the human body (global motion). Despite the great progress achieved by these approaches, they are not robust to global motion, and lack the ability to accurately predict local motion with a small movement range. To alleviate these two problems, we propose a relative information encoding method that yields positional and temporal enhanced representations. Firstly, we encode positional information by utilizing relative coordinates of 2D poses to enhance the consistency between the input and output distribution. The same posture with different absolute 2D positions can be mapped to a common representation. It is beneficial to resist the interference of global motion on the prediction results. Second, we encode temporal information by establishing the connection between the current pose and other poses of the same person within a period of time. More attention will be paid to the movement changes before and after the current pose, resulting in better prediction performance on local motion with a small movement range. The ablation studies validate the effectiveness of the proposed relative information encoding method. Besides, we introduce a multi-stage optimization method to the whole framework to further exploit the positional and temporal enhanced representations. Our method outperforms state-of-the-art methods on two public datasets. Code is available at https://github.com/paTRICK-swk/Pose3D-RIE.

show abstract

Section: Positional Informationmentioning

confidence: 99%

Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation

Wenkang

Wang

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Xu et al [28] makes use of a series of neural networks to perform pose estimation. An initial network is trained to learn the intrinsic parameters of a video sequence by comparing the projection of 3D ground truth joint positions to the 2D joint estimate.…”

Section: Single Camera 3d Human Pose Estimationmentioning

confidence: 99%

Temporally Consistent 3D Human Pose Estimation Using Dual 360° Cameras

Shere

Kim

Hilton

2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

This paper presents a 3D human pose estimation system that uses a stereo pair of 360°sensors to capture the complete scene from a single location. The approach combines the advantages of omnidirectional capture, the accuracy of multiple view 3D pose estimation and the portability of monocular acquisition. Joint monocular belief maps for joint locations are estimated from 360°images and are used to fit a 3D skeleton to each frame. Temporal data association and smoothing is performed to produce accurate 3D pose estimates throughout the sequence. We evaluate our system on the Panoptic Studio dataset, as well as real 360°v ideo for tracking multiple people, demonstrating an average Mean Per Joint Position Error of 12.47cm with 30cm baseline cameras. We also demonstrate improved capabilities over perspective and 360°multi-view systems when presented with limited camera views of the subject.

show abstract

“…In the light of exploring spatial-temporal learning, [21] use the entire video as the context for predicting the bone direction along with a consistent bone length across the entire video. [22] proposed a multi-step refinement and estimation framework that refines the 2D input keypoint sequence and then concurrently considering the structure of 2D inputs and 3D outputs. Interestingly, another family of methods [23,24,25] train deep models to directly model the human shape represented by SMPL [26] and perform reverse inference from the shape to the corresponding pose.…”

Section: D Pose Estimationmentioning

confidence: 99%

3D Pose Estimation and Future Motion Prediction from 2D Images

Yang

Zuo

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences. Based on Lie algebra pose representation, a novel self-projection mechanism is proposed that naturally preserves human motion kinematics. This is further facilitated by a sequence-to-sequence multi-task architecture based on an encoder-decoder topology, which enables us to tap into the common ground shared by both tasks. Finally, a global refinement module is proposed to boost the performance of our framework. The effectiveness of our approach, called PoseMoNet, is demonstrated by ablation tests and empirical evaluations on Human3.6M and HumanEva-I benchmark, where competitive performance is obtained comparing to the state-of-the-arts.

show abstract

Deep Kinematics Analysis for Monocular 3D Human Pose Estimation

Cited by 163 publications

References 43 publications

Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation

Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation

Temporally Consistent 3D Human Pose Estimation Using Dual 360° Cameras

3D Pose Estimation and Future Motion Prediction from 2D Images

Contact Info

Product

Resources

About