Filters








3,101 Hits in 7.8 sec

Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image [article]

Jameel Malik, Ahmed Elhayek, Didier Stricker
2017 arXiv   pre-print
In this work, we introduce a novel hybrid algorithm for estimating the 3D hand pose as well as bone-lengths of the hand skeleton at the same time, from a single depth image.  ...  The proposed CNN architecture learns hand pose parameters and scale parameters associated with the bone-lengths simultaneously.  ...  A novel hybrid approach for simultaneous estimation of 3D hand pose and bone-lengths of hand skeleton. 2.  ... 
arXiv:1712.03121v1 fatcat:26dlzssrgjdn3kzedqek5o3kua

Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image [article]

Fuyang Huang, Ailing Zeng, Minhao Liu, Jing Qin, Qiang Xu
2018 arXiv   pre-print
In this paper, we propose a novel structure-aware 3D hourglass network for hand pose estimation from a single depth image, which achieves state-of-the-art results on MSRA and NYU datasets.  ...  Final estimation can then be easily obtained from voxel density map with simple post-processing.  ...  Conclusion In this paper, we propose a structure-aware 3D hourglass network to estimate hand pose from single depth image.  ... 
arXiv:1812.10320v1 fatcat:hfpfpftft5fq7nmazxdrbpgj5u

DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth [article]

Jameel Malik, Ahmed Elhayek, Fabrizio Nunnari, Kiran Varanasi, Kiarash Tamaddon, Alexis Heloir, Didier Stricker
2018 arXiv   pre-print
a single depth image.  ...  Also, by employing a joint training strategy with real and synthetic data, we recover 3D hand mesh and pose from real images in 3.7ms.  ...  01IW15003) and VIDETE (Grant number 01IW18002).  ... 
arXiv:1808.09208v1 fatcat:gwzkoqq6vne63gsxbrbbkisq74

Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation [article]

Jiayi Wang, Franziska Mueller, Florian Bernard, Christian Theobalt
2021 arXiv   pre-print
We propose to use a model-based generative loss for training hand pose estimators on depth images based on a volumetric hand model.  ...  This additional loss allows training of a hand pose estimator that accurately infers the entire set of 21 hand keypoints while only using supervision for 6 easy-to-annotate keypoints (fingertips and wrist  ...  pose. • Despite ambiguities resulting from the reduced annotations, our method can simultaneously infer pose and bone lengths at test time  ... 
arXiv:2007.03073v2 fatcat:7ar5ocuxqbchxacufwdexb55n4

Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation

Jiayi Wang, Franziska Mueller, Florian Bernard, Christian Theobalt
2020 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)  
We propose to use a model-based generative loss for training hand pose estimators on depth images based on a volumetric hand model.  ...  This additional loss allows training of a hand pose estimator that accurately infers the entire set of 21 hand keypoints while only using supervision for 6 easy-to-annotate keypoints (fingertips and wrist  ...  pose. • Despite ambiguities resulting from the reduced annotations, our method can simultaneously infer pose and bone lengths at test time  ... 
doi:10.1109/fg47880.2020.00013 fatcat:p4zr3xk54varhkg4cip4hc4sni

WHSP-Net: A Weakly-Supervised Approach for 3D Hand Shape and Pose Recovery from a Single Depth Image

Jameel Malik, Ahmed Elhayek, Didier Stricker
2019 Sensors  
Although there are many hand pose estimation methods, only a few deep learning based algorithms target 3D hand shape and pose from a single RGB or depth image.  ...  For this reason, we propose a novel weakly-supervised approach for 3D hand shape and pose recovery (named WHSP-Net) from a single depth image by learning shapes from unlabeled real data and labeled synthetic  ...  CNN-based 3D hand pose estimation from a single depth image has been extensively studied in recent years.  ... 
doi:10.3390/s19173784 fatcat:ifjmcrwonnhjzbnmmya5v5prk4

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation [article]

Jianan Zhen, Qi Fang, Jiaming Sun, Wentao Liu, Wei Jiang, Hujun Bao, Xiaowei Zhou
2020 arXiv   pre-print
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view.  ...  Such a single-shot bottom-up scheme allows the system to better learn and reason about the inter-person depth relationship, improving both 3D and 2D pose estimation.  ...  This paper aims to address the problem of estimating absolute 3D poses of multiple people simultaneously from a single RGB image.  ... 
arXiv:2008.11469v1 fatcat:xmfqbsjwtfd7ddy3rdtdu53zwy

Augmented Skeleton Space Transfer for Depth-Based Hand Pose Estimation

Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose variations.  ...  Since the skeleton entries generated in this way do not have the corresponding depth map entries, we exploit them by training a separate hand pose generator (HPG) which synthesizes the depth map from the  ...  Kwang In Kim thanks EPSRC EP/M00533X/2 and RCUK EP/M023281/1.  ... 
doi:10.1109/cvpr.2018.00869 dblp:conf/cvpr/BaekKK18 fatcat:cf3y5t2stnesjeyid5wf5otbpi

Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation [article]

Seungryul Baek and Kwang In Kim and Tae-Kyun Kim
2018 arXiv   pre-print
Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose variations.  ...  Since the skeleton entries generated in this way do not have the corresponding depth map entries, we exploit them by training a separate hand pose generator (HPG) which synthesizes the depth map from the  ...  Kwang In Kim thanks EPSRC EP/M00533X/2 and RCUK EP/M023281/1.  ... 
arXiv:1805.04497v1 fatcat:pqf2qc75rbdh3fegxvorejqbl4

Modelling Simulation and Performance Analysis for Footwear Manufacturing System

2021 Computer Engineering and Intelligent Systems  
In the skeleton fitting stage, the 3D pose of every object is estimated by maximizing an objective function that combines a skeleton fitting term with motion and pose priors.  ...  It consists of the following stages: dynamic objects counting, objects specific 3D skeletons generation, initial 3D poses estimation, and 3D skeleton fitting which fits each 3D skeleton to the corresponding  ...  [60] is a new method that estimates the 3D pose of hands, face, and body from a single RGB image.  ... 
doi:10.7176/ceis/12-1-01 fatcat:4dtqx5tlonbgzfktipfysakyca

Lifting 2d Human Pose to 3d : A Weakly Supervised Approach [article]

Sandika Biswas, Sanjana Sinha, Kavya Gupta, Brojeshwar Bhowmick
2019 arXiv   pre-print
Estimating 3d human pose from monocular images is a challenging problem due to the variety and complexity of human poses and the inherent ambiguity in recovering depth from the single view.  ...  Few approaches have utilized training images from both 3d and 2d pose datasets in a weakly-supervised manner for learning 3d poses in unconstrained settings.  ...  ambiguity of estimating depth from a single view.  ... 
arXiv:1905.01047v1 fatcat:pybcweomxva75ms2qeksqxjuaq

Accurate realtime full-body motion capture using a single depth camera

Xiaolin Wei, Peizhao Zhang, Jinxiang Chai
2012 ACM Transactions on Graphics  
Figure 1 : Our system automatically and accurately reconstructs 3D skeletal poses in real time using monocular depth data obtained from a single camera.  ...  At the core of our system lies a realtime registration process that accurately reconstructs 3D human poses from single monocular depth images, even in the case of significant occlusions.  ...  IIS-1065384 and IIS-1055046.  ... 
doi:10.1145/2366145.2366207 fatcat:pxjeckp2nvhtlinn2teqjw4wyi

RGBD-Dog: Predicting Canine Pose from RGBD Sensors [article]

Sinead Kearney, Wenbin Li, Martin Parsons, Kwang In Kim, Darren Cosker
2020 arXiv   pre-print
In our work, we focus on the problem of 3D canine pose estimation from RGBD images, recording a diverse range of dog breeds with several Microsoft Kinect v2s, simultaneously obtaining the 3D ground truth  ...  We generate a dataset of synthetic RGBD images from this data. A stacked hourglass network is trained to predict 3D joint locations, which is then constrained using prior models of shape and pose.  ...  and the Settlement Research Fund (1.190058.01) of the Ulsan National Institute of Science & Technology.  ... 
arXiv:2004.07788v1 fatcat:zx22zewed5hrjiwitxcaciwzmi

EllipBody: A Light-weight and Part-based Representation for Human Pose and Shape Recovery [article]

Min Wang, Feng Qiu, Wentao Liu, Chen Qian, Xiaowei Zhou, Lizhuang Ma
2020 arXiv   pre-print
Extensive experiments show that our methods achieve the state-of-the-art results on Human3.6M and LSP dataset for 3D pose estimation and part segmentation.  ...  Human pose and shape recovery is an important task in computer vision and real-world understanding. Current works are tackled due to the lack of 3D annotations for whole body shapes.  ...  Introduction Recovering human shape from a single image is a challenging task in the computer vision area. This task aims at predicting both human pose and shape parameters simultaneously.  ... 
arXiv:2003.10873v1 fatcat:bwp3nfnjyfflvgav37onhvhahe

Two-hand Global 3D Pose Estimation Using Monocular RGB [article]

Fanqing Lin, Connor Wilhelm, Tony Martinez
2020 arXiv   pre-print
Global joint locations with respect to the camera origin are computed using the hand pose estimations and the actual length of the key bone with a novel projection algorithm.  ...  We propose a novel multi-stage convolutional neural network based pipeline that accurately segments and locates the hands despite occlusion between two hands and complex background noise and estimates  ...  Given a single RGB image as input, we use HandSeg-Net to simultaneously obtain the segmentation masks and the heatmap energy of both hands.  ... 
arXiv:2006.01320v4 fatcat:axg2q7zwqjdw5ku47km3kyu4hm
« Previous Showing results 1 — 15 out of 3,101 results