Filters








20,305 Hits in 7.1 sec

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  ...  novel weakly-supervised method for a highly challenging problem of 3D hand shape and pose estimation from a single depth image.  ... 
doi:10.3390/s19173784 fatcat:ifjmcrwonnhjzbnmmya5v5prk4

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.  ...  In this study, we present a comprehensive survey of state-of-the-art 3D hand shape and pose estimation approaches using RGB-D cameras.  ...  SRN [72] proposed a simple and effective method for 3D hand pose estimation from a 2D depth image by stacking multiple differentiable re-parameterization modules, which construct 3D heatmaps and unit  ... 
doi:10.1016/j.vrih.2021.05.002 fatcat:4tbhftt3ira6fporaqlscqhsse

HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation [article]

Zhaohui Zhang and Shipeng Xie and Mingxiu Chen and Haichao Zhu
2020 arXiv   pre-print
Second, we introduce a simple and effective method to synthesize data by combining real and synthetic image together in the image space.  ...  Hand pose estimation from 3D depth images, has been explored widely using various kinds of techniques in the field of computer vision.  ...  The 2D deep learning based approaches estimate hand pose directly from depth images.  ... 
arXiv:2001.00702v2 fatcat:6isfopuzyffenind57fe2pheey

A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection

Seong-heum Kim, Youngbae Hwang
2021 Electronics  
Owing to recent advancements in deep learning methods and relevant databases, it is becoming increasingly easier to recognize 3D objects using only RGB images from single viewpoints.  ...  Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized.  ...  Acknowledgments: The first author sincerely appreciates Min-ho Lee and Hoo-kyeong Lee at KETI for valuable discussion. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics10040517 fatcat:rziqhrkefvelpg3vgb6qxfprte

Learning camera viewpoint using CNN to improve 3D body pose estimation [article]

Mona Fathollahi Ghezelghieh, Rangachar Kasturi, Sudeep Sarkar
2016 arXiv   pre-print
The objective of this work is to estimate 3D human pose from a single RGB image.  ...  Extracting image representations which incorporate both spatial relation of body parts and their relative depth plays an essential role in accurate3D pose reconstruction.  ...  However, there is still a great need to infer 3D pose from a single RGB image which is our focus in this paper.  ... 
arXiv:1609.05522v1 fatcat:77uajppkdffwjegpp2zxfgwhg4

HBE: Hand Branch Ensemble Network for Real-Time 3D Hand Pose Estimation [chapter]

Yidan Zhou, Jian Lu, Kuo Du, Xiangbo Lin, Yi Sun, Xiaohong Ma
2018 Lecture Notes in Computer Science  
The goal of this paper is to estimate the 3D coordinates of the hand joints from a single depth image.  ...  In addition, a feature ensemble layer along with a low-dimensional embedding layer ensures the overall hand shape constraints.  ...  Recently, learning based approaches have achieved remarkable performance in hand pose estimation from a single depth image.  ... 
doi:10.1007/978-3-030-01264-9_31 fatcat:2owfipezc5eyxpj7vppc442gva

End-to-end Hand Mesh Recovery from a Monocular RGB Image [article]

Xiong Zhang and Qiang Li and Hong Mo and Wenbo Zhang and Wen Zheng
2019 arXiv   pre-print
In contrast to existing research on 2D or 3D hand pose estimation from RGB or/and depth image data, HAMR can provide a more expressive and useful mesh representation for monocular hand image understanding  ...  for both 2D and 3D hand pose estimation from a monocular RGB image on several benchmark datasets.  ...  [16] introduced a simple yet effective deep learning architecture for 2D hand pose estimation and also built a multi-view 3D hand pose dataset.  ... 
arXiv:1902.09305v3 fatcat:n7t45acxfzhifiiedd3d54v4l4

Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation [article]

Ziwei Yu, Linlin Yang, Shicheng Chen, Angela Yao
2021 arXiv   pre-print
This paper addresses the 3D point cloud reconstruction and 3D pose estimation of the human hand from a single RGB image.  ...  To that end, we present a novel pipeline for local and global point cloud reconstruction using a 3D hand template while learning a latent representation for pose estimation.  ...  Handvoxnet: Deep voxel- based network for 3d hand shape and pose estimation from a single depth map.  ... 
arXiv:2112.06389v1 fatcat:n6zujacknrfqllnld4vaulia5m

Real-time pose and shape reconstruction of two interacting hands with a single depth camera

Franziska Mueller, Micah Davis, Florian Bernard, Oleksandr Sotnychenko, Mickeal Verschoor, Miguel A. Otaduy, Dan Casas, Christian Theobalt
2019 ACM Transactions on Graphics  
In order to achieve this, we embed a recent parametric hand pose and shape model and a dense correspondence predictor based on a deep neural network into a suitable energy minimization framework.  ...  We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands.  ...  The work was supported by the ERC Consolidator Grants 4DRepLy (770784) and TouchDesign (772738). Dan Casas was supported by a Marie Curie Individual Fellowship (707326).  ... 
doi:10.1145/3306346.3322958 fatcat:no6xzoth3bclhiwgsya7p4ajqy

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
In our simple non-parametric solution, the generated Peeled Depth maps are back-projected to 3D space to obtain a complete textured 3D shape.  ...  We train PeelGAN using a 3D Chamfer loss and other 2D losses to generate multiple depth values per-pixel and a corresponding RGB field per-vertex in a dual-branch setup.  ...  Volumetric regression [35, 37, 13 ] uses a voxel grid, i.e., a binary occupancy map to recover the human body from a single RGB image.  ... 
arXiv:2002.06664v2 fatcat:itfkq7qf6vc3jhoa4qmgnatnr4

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map [article]

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
2018 arXiv   pre-print
Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates  ...  To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel  ...  Analyzing previ-ous deep learning-based methods for 3D hand and human pose estimation from a single depth image, most of these methods [1, 3, 7, 14-16, 24, 29-31, 47] are based on a common framework  ... 
arXiv:1711.07399v3 fatcat:jtp3hizwunglbcn3erid2pavaa

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

Ju Yong Chang, Gyeongsik Moon, Kyoung Mu Lee
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates  ...  To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel  ...  Acknowledgments This work was supported by the Visual Turing Test project (IITP-2017-0-01780) from the Ministry of Science and ICT of Korea.  ... 
doi:10.1109/cvpr.2018.00533 dblp:conf/cvpr/MoonCL18 fatcat:m6kskcckxjhehmuu54l256tsaq

Silhouette-Net: 3D Hand Pose Estimation from Silhouettes [article]

Kuo-Wei Lee, Shih-Hung Liu, Hwann-Tzong Chen, Koichi Ito
2019 arXiv   pre-print
We present a new architecture that automatically learns a guidance from implicit depth perception and solves the ambiguity of hand pose through end-to-end training.  ...  3D hand pose estimation has received a lot of attention for its wide range of applications and has made great progress owing to the development of deep learning.  ...  More recent methods aim to estimate the 3D hand pose from a single RGB image using deep neural networks (Zimmermann and Brox 2017; Tome, Russell, and Agapito 2017) owing to the advance in deep learning  ... 
arXiv:1912.12436v1 fatcat:5azdtyp4mnesnpla3peuwwqehy

DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation [article]

Markus Oberweger, Vincent Lepetit
2017 arXiv   pre-print
DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map.  ...  Here we show that with simple improvements: adding ResNet layers, data augmentation, and better initial hand localization, we achieve better or similar performance than more sophisticated recent methods  ...  DeepPrior is a Deep Network-based approach that uses a single depth image as input and directly predicts the 3D joint locations of the hand skeleton.  ... 
arXiv:1708.08325v1 fatcat:3xq6ijt5evh2rfrh4wy6bb2snq

DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation

Markus Oberweger, Vincent Lepetit
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
DeepPrior [18] is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map.  ...  Here we show that with simple improvements: adding ResNet layers, data augmentation, and better initial hand localization, we achieve better or similar performance than more sophisticated recent methods  ...  DeepPrior is a Deep Network-based approach that uses a single depth image as input and directly predicts the 3D joint locations of the hand skeleton.  ... 
doi:10.1109/iccvw.2017.75 dblp:conf/iccvw/OberwegerL17 fatcat:plqhuw674fabdlgeq7g6gz5zjm
« Previous Showing results 1 — 15 out of 20,305 results