Proceedings Article10.1145/3528233.3530746
QuickPose: Real-time Multi-view Multi-person Pose Estimation in Crowded Scenes
Zhize Zhou,Qing Shuai,Yize Wang,Qihang Fang,Xiaopeng Ji,Fashuai Li,Hujun Bao,Xiaowei Zhou +7 more
- 27 Jul 2022
9
TL;DR: This work forms the multi-view matching problem as mode seeking in the space of skeleton proposals and develops an efficient algorithm named QuickPose to solve the problem, which enables real-time motion capture in crowded scenes.
read more
Abstract: This work proposes a real-time algorithm for reconstructing 3D human poses in crowded scenes from multiple calibrated views. The key challenge of this problem is to efficiently match 2D observations across multiple views. Previous methods perform multi-view matching either at the full-body level, which is sensitive to 2D pose estimation error, or at the part level, which ignores 2D constraints between different types of body parts in the same view. Instead, our approach reasons about all plausible skeleton proposals during multi-view matching, where each skeleton may consist of an arbitrary number of parts instead of being a whole body or a single part. To this end, we formulate the multi-view matching problem as mode seeking in the space of skeleton proposals and develop an efficient algorithm named QuickPose to solve the problem, which enables real-time motion capture in crowded scenes. Experiments show that the proposed algorithm achieves the state-of-the-art performance in terms of both speed and accuracy on public datasets.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
From motion to magic: Real-time virtual-real stage effects via 3D motion capture
Xiongbin Lin,Xun Wang,Wenwu Yang +2 more
- 15 Nov 2023
TL;DR: A real-time generation system for stage visual effects based on multi-view multi-person 3D motion capture technique that effectively enhanced the sense of presence and interactivity of the stage performance, providing actors with more freedom and control in their performances.
3
From Method to Application: A Review of Deep 3D Human Motion Capture
Zehai Niu,Ke Lü,Jian Xue,Xiaohong Qin,Jinbao Wang,Ling Shao +5 more
2
Skeleton Cluster Tracking for robust multi-view multi-person 3D human pose estimation
Zehai Niu,Ke Lü,Jian Xue,Jinbao Wang +3 more
TL;DR: The proposed "Skeleton Pooling-Clustering-Tracking" paradigm robustly estimates 3D human pose from multiple views by refining and filtering skeleton clusters.
2
Reconstructing Close Human Interactions from Multiple Views
Qing Shuai,Zhiyuan Yu,Zhize Zhou,Lixin Fan,Haijun Yang,Can Yang,Xiaowei Zhou +6 more
TL;DR: This paper addresses the challenging task of reconstructing the poses of multiple individuals engaged in close interactions, captured by multiple calibrated cameras by integrating a learning-based pose estimation component and its corresponding training and inference strategies.
1
Real-Time Multi-View Human Pose Estimation System
Yuan Yang,Yangang Wang +1 more
- 07 Jun 2024
TL;DR: A multi-view multi-person pose estimation algorithm framework that fulfills real-time requirements and achieves an average frame rate of 40FPS in experimental settings while demonstrating robustness against human motion and occlusion is developed.
1
References
Mean shift: a robust approach toward feature space analysis
Dorin Comaniciu,Peter Meer +1 more
TL;DR: It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.
12.9K
On Estimation of a Probability Density Function and Mode
TL;DR: In this paper, the problem of the estimation of a probability density function and of determining the mode of the probability function is discussed. Only estimates which are consistent and asymptotically normal are constructed.
Stacked Hourglass Networks for Human Pose Estimation
Alejandro Newell,Kaiyu Yang,Jia Deng +2 more
- 08 Oct 2016
TL;DR: This work introduces a novel convolutional network architecture for the task of human pose estimation that is described as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions.
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Zhe Cao,Tomas Simon,Shih-En Wei,Yaser Sheikh +3 more
- 21 Jul 2017
TL;DR: Part Affinity Fields (PAFs) as discussed by the authors uses a nonparametric representation to learn to associate body parts with individuals in the image and achieves state-of-the-art performance on the MPII Multi-Person benchmark.
6.2K
Deep High-Resolution Representation Learning for Human Pose Estimation
Ke Sun,Bin Xiao,Dong Liu,Jingdong Wang +3 more
- 25 Feb 2019
TL;DR: This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.