Article
Computer Science, Artificial Intelligence
Xiaoming Deng, Dexin Zuo, Yinda Zhang, Zhaopeng Cui, Jian Cheng, Ping Tan, Liang Chang, Marc Pollefeys, Sean Fanello, Hongan Wang
Summary: This paper investigates the impact of view-independent features on 3D hand pose estimation from a single depth image, and proposes a novel recurrent neural network model for 3D hand pose estimation. The model uses a cascaded 3D pose-guided alignment strategy for view-independent feature extraction and a recurrent hand pose module for modeling the dependencies among sequential aligned features. Experiments show that this method significantly improves the state-of-the-art accuracy on popular benchmarks with simple yet efficient alignment and network architectures.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Xingyuan Zhang, Fuhai Zhang
Summary: This paper proposes a novel Differentiable Spatial Regression method for 3D hand pose estimation, which combines the advantages of regression-based and detection-based methods. A specific model named SRNet is designed, utilizing a combination of 2D heatmaps and local offset maps to improve the accuracy and effectiveness of the estimation.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Engineering, Electrical & Electronic
Xiang-Bo Lin, Yi-Dan Zhou, Kuo Du, Yi Sun, Xiao-Hong Ma, Jian Lu
Summary: This work addresses the challenging problem of estimating the full 3D hand pose when a hand interacts with an unknown object. By focusing on extracting more effective features through multi-level fusion design, the proposed method demonstrates state-of-the-art performance on a public hand-object interaction dataset.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Shaoxiang Guo, Eric Rigall, Lin Qi, Xinghui Dong, Haiyan Li, Junyu Dong
Summary: The paper explores the prediction of 3D hand poses from a single RGB image, utilizing multiple feature maps, graph-based convolutional neural networks, and self-supervised modules to improve the accuracy of hand pose estimation.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Asako Kanezaki, Yasuyuki Matsushita, Yoshifumi Nishida
Summary: RotationNet is a CNN-based model that jointly estimates the pose and category of an object using multi-view images, without the need for known viewpoint labels. It demonstrates superior performance in 3D object classification and pose estimation, and achieved first place in a 3D Shape Retrieval Contest.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Donghai Xiang, Wei Xu, Yuting Zhang, Bei Peng, Guotai Wang, Kang Li
Summary: The high performance of deep learning methods for 3D hand pose estimation relies on a large annotated training set. To reduce annotation cost, we propose a semi-supervised method based on Multi-Task and Multi-View Consistency (MTMVC) for hand pose estimation. Experimental results show that our proposed MTMVC outperforms existing semi-supervised methods and achieves comparable accuracy to state-of-the-art fully supervised methods, using only half of the annotations.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2023)
Review
Computer Science, Artificial Intelligence
Yann Desmarais, Denis Mottet, Pierre Slangen, Philippe Montesinos
Summary: Human pose estimation is a crucial research field with important applications in robotics, entertainment, health, and sports sciences. Recent advancements in convolutional networks have led to significant improvements in 2D pose estimation and reduced the average error in modern 3D markerless motion capture techniques. However, the increasing number of methods in this field has made it challenging to make informed choices. Researchers have proposed a taxonomy based on accuracy, speed, and robustness to categorize methods and provide guidance for future research.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Article
Engineering, Electrical & Electronic
Moran Li, Jialong Wang, Nong Sang
Summary: A novel compressed latent distribution representation is proposed to address the channel correspondence problem in 3D hand pose estimation from monocular RGB images. By interconnecting 2D and depth feature maps more directly, the proposed method effectively improves cross-dataset performance and achieves state-of-the-art results on benchmark datasets.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Omar Del-Tejo-Catala, Jose-Luis Guardiola, Javier Perez, David Millan Escriva, Alberto J. Perez, Juan-Carlos Perez-Cortes
Summary: This paper proposes a novel probabilistic algorithm for pose estimation that addresses issues such as partial occlusion, object symmetries, and multiple correct poses. The algorithm combines information from multiple cameras to achieve accurate predictions. Testing on synthetic objects shows that the algorithm can handle these issues with a certain level of accuracy. Comparisons with state-of-the-art methodologies demonstrate that the algorithm can compete in terms of accuracy.
Article
Computer Science, Artificial Intelligence
Boshen Zhang, Yang Xiao, Fu Xiong, Cunlin Wu, Zhiguo Cao, Ping Liu, Joey Tianyi Zhou
Summary: This paper aims to address two major research problems in 3D human pose estimation using depth data. Firstly, it proposes a crossmodality CNN training strategy to transfer RGB annotation information to the depth domain. Secondly, it introduces a multi-scale local refinement network to effectively handle the optimal local observation scale.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Qing Gao, Yongquan Chen, Zhaojie Ju, Yi Liang
Summary: This paper proposes a dynamic hand gesture recognition method based on 3D hand pose estimation, which improves the recognition accuracy by using data fusion and deep neural network. The proposed method is verified to be reliable and efficient in experiments.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Honghong Yang, Hongxi Liu, Yumei Zhang, Xiaojun Wu
Summary: This paper proposes a hierarchical parallel multi-scale graph convolutional network (HPM-GNet) for 3D human pose estimation. The network addresses the problem of feature assimilation in graph convolutional networks and achieves state-of-the-art performance on benchmark datasets.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Jae-Hun Song, Suk-Ju Kang
Summary: Hand pose estimation from a single depth image has attracted significant attention recently due to its importance in various applications involving human-computer interaction. The proposed CNN-based approach incorporates hand joint connections to features through both global and local relation inference, outperforming previous state-of-the-art methods on public datasets. The method also boasts real-time application potential with an execution speed of 103 fps in a single GPU environment.
Article
Chemistry, Analytical
Peng Ji, Xianjian Wang, Fengying Ma, Jinxiang Feng, Chenglong Li
Summary: This paper proposes a 3D hand attitude estimation approach using CNN and LightGBM based on dual-view RGB images. It combines ensemble learning and deep learning to build an integrated hand attitude CNN regression model, and establishes a mapping from 2D images to 3D hand attitude angles using a training approach for feature integration.
Article
Chemistry, Analytical
Xiaojing Sun, Bin Wang, Longxiang Huang, Qian Zhang, Sulei Zhu, Yan Ma
Summary: In this paper, a novel RGB and depth information fusion network called CrossFuNet is proposed to improve the accuracy of 3D hand pose estimation. By inputting the RGB image and paired depth map into two separate subnetworks and combining feature maps in the fusion module using a new approach to merge information from both modalities, accurate 3D hand pose estimation is achieved. The model is validated on two public datasets and outperforms state-of-the-art methods.
Article
Computer Science, Software Engineering
Ke Gu, Junfei Qiao, Xiongkuo Min, Guanghui Yue, Weisi Lin, Daniel Thalmann
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2018)
Article
Automation & Control Systems
Hui Liang, Junsong Yuan, Jun Lee, Liuhao Ge, Daniel Thalmann
IEEE TRANSACTIONS ON CYBERNETICS
(2019)
Article
Computer Science, Artificial Intelligence
Ke Gu, Vinit Jakhetiya, Jun-Fei Qiao, Xiaoli Li, Weisi Lin, Daniel Thalmann
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Liuhao Ge, Hui Liang, Junsong Yuan, Daniel Thalmann
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2019)
Article
Computer Science, Software Engineering
Nisha Jain, Andrzej Wydra, Wen Hai, Nadia Magnenat Thalmann, Daniel Thalmann
Editorial Material
Computer Science, Software Engineering
Soraia Raupp Musse, Daniel Thalmann, Rafael Bidarra
COMPUTERS & GRAPHICS-UK
(2018)
Article
Multidisciplinary Sciences
Yasir Tahir, Zixu Yang, Debsubhra Chakraborty, Nadia Thalmann, Daniel Thalmann, Yogeswary Maniam, Nur Amirah Binte Abdul Rashid, Bhing-Leet Tan, Jimmy Lee Chee Keong, Justin Dauwels
Proceedings Paper
Computer Science, Software Engineering
Li Tian, Nadia Magnenat Thalmann, Daniel Thalmann, Zhiwen Fang, Jianmin Zheng
ADVANCES IN COMPUTER GRAPHICS, CGI 2019
(2019)
Proceedings Paper
Engineering, Electrical & Electronic
Shihao Xu, Zixu Yang, Debsubhra Chakraborty, Yasir Tahir, Tomasz Maszczyk, Victoria Yi Han Chua, Justin Dauwels, Daniel Thalmann, Nadia Magnenat, Thalmann Bhing-Leet Tan, Jimmy Lee Chee Keong
2018 IEEE 23RD INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP)
(2018)
Proceedings Paper
Computer Science, Theory & Methods
Daniel Thalmann, Nadia Magnenat Thalmann, Manoj Ramanathan
SA'17: SIGGRAPH ASIA 2017 COURSES
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Hui Liang, Junhui Hou, Junsong Yuan, Daniel Thalmann
COMPUTER VISION - ACCV 2016, PT III
(2017)
Proceedings Paper
Engineering, Electrical & Electronic
Daniel Thalmann
FRONTIERS IN ELECTRONIC TECHNOLOGIES: TRENDS AND CHALLENGES
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Liuhao Ge, Hui Liang, Junsong Yuan, Daniel Thalmann
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Robotics
Li Tian, Nadia Magnenat Thalmann, Daniel Thalmann, Jianmin Zheng
FRONTIERS IN ROBOTICS AND AI
(2017)