Filters








74,690 Hits in 9.4 sec

Learning an efficient model of hand shape variation from depth images

Sameh Khamis, Jonathan Taylor, Jamie Shotton, Cem Keskin, Shahram Izadi, Andrew Fitzgibbon
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The model is built from a set of noisy depth images of a diverse set of subjects performing different poses with their hands.  ...  We describe how to learn a compact and efficient model of the surface deformation of human hands.  ...  Fitting the Model A major contribution of this work is showing how to learn the parameters Υ from a set of noisy depth images of users' hands.  ... 
doi:10.1109/cvpr.2015.7298869 dblp:conf/cvpr/KhamisTSKIF15 fatcat:qymkprwevfeqxotr5jjr2fzc34

User-Independent American Sign Language Alphabet Recognition Based on Depth Image and PCANet Features

Walaa Aly, Saleh Alya, Sultan Almotairi
2019 IEEE Access  
Two strategies of learning the PCANet model are proposed, namely to train a single PCANet model from samples of all users and to train a separate PCANet model for each user, respectively.  ...  The performance of the proposed method is evaluated using public dataset of real depth images captured from various users.  ...  Hand shape features are learned through the efficient PCANet deep learning architecture.  ... 
doi:10.1109/access.2019.2938829 fatcat:ogza6lq56vgznpk25n6tbdg6pe

PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction [article]

Sai Sagar Jinka, Rohan Chacko, Avinash Sharma, P. J. Narayanan
2020 arXiv   pre-print
Given a monocular RGB image, we learn these Peeled maps in an end-to-end generative adversarial fashion using our novel framework - PeelGAN.  ...  PeeledHuman encodes the human body as a set of Peeled Depth and RGB maps in 2D, obtained by performing ray-tracing on the 3D body model and extending each ray beyond its first intersection.  ...  Majority of existing deep learning methods to recover 3D shapes from monocular RGB images use parametric SMPL [20] model.  ... 
arXiv:2002.06664v2 fatcat:itfkq7qf6vc3jhoa4qmgnatnr4

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.  ...  Particularly, the hybrid methods based on learning followed by model fitting or model based deep learning do not explicitly consider varying hand shapes and sizes.  ...  Acknowledgements This work was partially funded by the European project Eyes of Things (EoT) under contract number GA643924.  ... 
arXiv:1712.03121v1 fatcat:26dlzssrgjdn3kzedqek5o3kua

Survey on depth and RGB image-based 3D hand shape and pose estimation

Lin Huang, Boshen Zhang, Zhilin Guo, Yang Xiao, Zhiguo Cao, Junsong Yuan
2021 Virtual Reality & Intelligent Hardware  
hand shape and pose estimation.  ...  Nonetheless, the existence of complicated hand articulation, depth and scale ambiguities, occlusions, and finger similarity remain challenging.  ...  MANO model can be limited when representing complex hand shape variations owing to the use of linear bases for hand reconstruction.  ... 
doi:10.1016/j.vrih.2021.05.002 fatcat:4tbhftt3ira6fporaqlscqhsse

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  ...  Generative, model-based approaches. These methods iteratively refine an estimated pose by fitting a 3D hand model to the input depth image.  ... 
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  ...  Generative, model-based approaches. These methods iteratively refine an estimated pose by fitting a 3D hand model to the input depth image.  ... 
doi:10.1109/fg47880.2020.00013 fatcat:p4zr3xk54varhkg4cip4hc4sni

Online learning and fusion of orientation appearance models for robust rigid object tracking

Ioannis Marras, Georgios Tzimiropoulos, Stefanos Zafeiriou, Maja Pantic
2014 Image and Vision Computing  
More specifically, our framework combines image gradient orientations as extracted from intensity images with the directions of surface normals computed from dense depth fields.  ...  The robustness of learning from orientation appearance models is presented theoretically and experimentally in this work.  ...  More specifically, our method learns orientation appearance models from image gradient orientations as extracted from intensity images and the directions of surface normals computed from dense depth fields  ... 
doi:10.1016/j.imavis.2014.04.017 fatcat:fsxgndn2cvfx7kr5elnmp5ek2i

Online learning and fusion of orientation appearance models for robust rigid object tracking

Ioannis Marras, Joan Alabort Medina, Georgios Tzimiropoulos, Stefanos Zafeiriou, Maja Pantic
2013 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
More specifically, our framework combines image gradient orientations as extracted from intensity images with the directions of surface normals computed from dense depth fields.  ...  The robustness of learning from orientation appearance models is presented theoretically and experimentally in this work.  ...  More specifically, our method learns orientation appearance models from image gradient orientations as extracted from intensity images and the directions of surface normals computed from dense depth fields  ... 
doi:10.1109/fg.2013.6553798 dblp:conf/fgr/MarrasATZP13 fatcat:eqckpkxqyvfu5l7qfeqjuh4fbu

3D car shape reconstruction from a contour sketch using GAN and lazy learning

Naoki Nozawa, Hubert P. H. Shum, Qi Feng, Edmond S. L. Ho, Shigeo Morishima
2021 The Visual Computer  
The system learns from a synthetic database of 3D car models and their corresponding 2D contour sketches and segmentation masks, allowing effective training with minimal data collection cost.  ...  GAN, being a deep learning method, is capable of modelling complicated data distributions, enabling the effective modelling of a large variety of cars.  ...  Since it is computationally inefficient to directly learn 3D shape representation from mesh, we propose to learn an intermediate representation of multiple depth images instead and reconstruct the 3D car  ... 
doi:10.1007/s00371-020-02024-y fatcat:q62huylxcjej7js2i7fqcme7kq

A Comprehensive Study on Deep Learning-Based 3D Hand Pose Estimation Methods

Theocharis Chatzis, Andreas Stergioulas, Dimitrios Konstantinidis, Kosmas Dimitropoulos, Petros Daras
2020 Applied Sciences  
The utilization of technological advances, such as cost-efficient depth cameras coupled with the explosive progress of Deep Neural Networks (DNNs), has led to a significant boost in the development of  ...  In this survey, we provide a comprehensive study of the most representative deep learning-based methods in literature and propose a new taxonomy heavily based on the input data modality, being RGB, depth  ...  At each frame, an algorithm performs an exploration in order to acquire the pose and shape of the hand model that best matches the features extracted from the input image.  ... 
doi:10.3390/app10196850 fatcat:hgyqkoyetbbilncksguarqz3bq

SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation [article]

John Yang, Hyung Jin Chang, Seungeui Lee, Nojun Kwak
2020 arXiv   pre-print
Our novel training strategy of detaching the recurrent layer of the framework during domain finetuning from synthetic to real allows preservation of the visuo-temporal features learned from sequential  ...  With the generated dataset, we train a newly proposed recurrent framework, exploiting visuo-temporal features from sequential images of synthetic hands in motion and emphasizing temporal smoothness of  ...  Acknowledgement This work was supported by IITP grant funded by the Korea government (MSIT) (No.2019-0-01367, Babymind) and Next-Generation Information Computing Development Program through the NRF of  ... 
arXiv:2007.05168v1 fatcat:ksmivqhqbnenxgfdtbcybowkiq

Combining discriminative and model based approaches for hand pose estimation

Philip Krejov, Andrew Gilbert, Richard Bowden
2015 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
Model fitting is guided using point to surface constraints which bind a kinematic model of the hand to the depth cloud using the segmentation of the discriminative approach.  ...  A Randomised Decision Forests (RDF) is used to provide an initial estimate of the regions of the hand.  ...  We utilise a rigid body simulation to perform an efficient fitting between the hand model and classified depth.  ... 
doi:10.1109/fg.2015.7163141 dblp:conf/fgr/KrejovGB15 fatcat:xyxl4esbuveqbmsjdilvltgws4

Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition [article]

Jian Liu, Naveed Akhtar, Ajmal Mian
2018 arXiv   pre-print
The learned CNN models are then used as invariant feature extractors from real RGB and depth frames of human action videos and the temporal variations are modelled by Fourier Temporal Pyramid.  ...  We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints.  ...  from scratch, we used real background images for efficiency and diversity of data.  ... 
arXiv:1707.00823v2 fatcat:poz2y4vr3vbohgssiwe7qgc7lu

Hybrid Deep Network and Polar Transformation Features for Static Hand Gesture Recognition in Depth Data

Vo Hoai, Tran Thai, Ly Quoc
2016 International Journal of Advanced Computer Science and Applications  
In this paper, we propose the effective hand segmentation from the full depth image that is important step before extracting the features to represent for hand gesture.  ...  We also represent the novel hand descriptor explicitly encodes the shape and appearance information from depth maps that are significant characteristics for static hand gestures.  ...  An extracted gesture feature can be considered an efficient representation if it could fulfill three criteria: firstly, it minimizes within-class variations while maximizes between-class variations; secondly  ... 
doi:10.14569/ijacsa.2016.070536 fatcat:mvdcrw3stndl5ozqv525v73jae
« Previous Showing results 1 — 15 out of 74,690 results