Filters








13 Hits in 4.0 sec

GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB

Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Figure 1 : We present an approach for real-time 3D hand tracking from monocular RGB-only input.  ...  Abstract We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence.  ...  Related Work Our goal is to track hand pose from unconstrained monocular RGB video streams at real-time framerates.  ... 
doi:10.1109/cvpr.2018.00013 dblp:conf/cvpr/MuellerBSM0CT18 fatcat:pw73umrjgjhdzpttehh3uljeu4

GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB [article]

Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt
2017 arXiv   pre-print
We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence.  ...  We demonstrate that our hand tracking system outperforms the current state-of-the-art on challenging RGB-only footage.  ...  Related Work Our goal is to track hand pose from unconstrained monocular RGB video streams at real-time framerates.  ... 
arXiv:1712.01057v1 fatcat:7jxgkuoogfbb5itjoq2wbpftpa

Weakly-Supervised 3D Hand Pose Estimation from Monocular RGB Images [chapter]

Yujun Cai, Liuhao Ge, Jianfei Cai, Junsong Yuan
2018 Lecture Notes in Computer Science  
Compared with depth-based 3D hand pose estimation, it is more challenging to infer 3D hand pose from monocular RGB images, due to substantial depth ambiguity and the difficulty of obtaining fullyannotated  ...  Different from existing learning-based monocular RGB-input approaches that require accurate 3D annotations for training, we propose to leverage the depth images that can be easily obtained from commodity  ...  Fig. 2 . 2 We present a weakly-supervised approach for 3D hand pose estimation from monocular RGB-only input.  ... 
doi:10.1007/978-3-030-01231-1_41 fatcat:ha3362vv7fbb3ptdman7e7cj6a

Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data [article]

Yuxiao Zhou and Marc Habermann and Weipeng Xu and Ikhsanul Habibie and Christian Theobalt and Feng Xu
2022 arXiv   pre-print
We present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accuracy.  ...  It features a 3D hand joint detection module and an inverse kinematics module which regresses not only 3D joint positions but also maps them to joint rotations in a single feed-forward pass.  ...  We present a novel hand motion capture approach that estimates 3D hand joint locations and rotations at real time from a single RGB image.  ... 
arXiv:2003.09572v3 fatcat:2opvkzzgijaqhobrlzhtqqnwji

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  
In this study, we present a comprehensive survey of state-of-the-art 3D hand shape and pose estimation approaches using RGB-D cameras.  ...  Related RGB-D cameras, hand datasets, and a performance analysis are also discussed to provide a holistic view of recent achievements.  ...  In contrast, here we consider the reconstruction of a 3D hand from a single monocular RGB frame, which cannot be directly used as the fitting object.  ... 
doi:10.1016/j.vrih.2021.05.002 fatcat:4tbhftt3ira6fporaqlscqhsse

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

John Yang, Hyung Jin Chang, Seungeui Lee, Nojun Kwak
2020 arXiv   pre-print
3D hand pose estimation based on RGB images has been studied for a long time. Most of the studies, however, have performed frame-by-frame estimation based on independent static images.  ...  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 sequential monocular RGB-D inputs, Taylor et al. [41] optimize surface hand shape models, updating subdivision surfaces on corresponding 3D hand geometric models.  ... 
arXiv:2007.05168v1 fatcat:ksmivqhqbnenxgfdtbcybowkiq

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints [article]

Adrian Spurr, Umar Iqbal, Pavlo Molchanov, Otmar Hilliges, Jan Kautz
2020 arXiv   pre-print
Estimating 3D hand pose from 2D images is a difficult, inverse problem due to the inherent scale and depth ambiguities.  ...  While annotations of 2D keypoints are much easier to obtain, how to efficiently leverage such weakly-supervised data to improve the task of 3D hand pose prediction remains an important open question.  ...  We are grateful to Christoph Gebhardt and Shoaib Ahmed Siddiqui for the aid in figure creation and Abhishek Badki for helpful discussions.  ... 
arXiv:2003.09282v2 fatcat:kex6gbtpojevfj6avz2ifhmqd4

HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge [article]

Jae Shin Yoon, Zhixuan Yu, Jaesik Park, Hyun Soo Park
2021 arXiv   pre-print
The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of five primary body signals including gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cameras  ...  This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing.  ...  Ganerated hands for real-time 3d forest: Structured estimation of 3d articulated hand posture. In hand tracking from monocular rgb.  ... 
arXiv:2110.00119v2 fatcat:bakqd343fzfonl3sv2f4zw4rra

Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction [article]

Mengshi Qi, Edoardo Remelli, Mathieu Salzmann, Pascal Fua
2020 arXiv   pre-print
Deep learning-solutions for hand-object 3D pose and shape estimation are now very effective when an annotated dataset is available to train them to handle the scenarios and lighting conditions they will  ...  encounter at test time.  ...  Theobalt, “Ganerated Hands for Real-Time 3D Hand Tracking from Monocular RGB  ... 
arXiv:2012.11260v1 fatcat:wzloca4avzbtfcumf26bek6dc4

Stereo Feature Learning based on Attention and Geometry for Absolute Hand Pose Estimation in Egocentric Stereo Views

Kyeongeun Seo, Hyeonjoong Cho, Daewoong Choi, Taewook Heo
2021 IEEE Access  
For example, RGB-based techniques have intrinsic difficulty in converting relative 3D poses into absolute 3D poses, and RGBD-based techniques only work in indoor environments.  ...  Egocentric hand pose estimation is significant for wearable cameras since the hand interactions are captured from an egocentric viewpoint.  ...  Although massive monocular RGB datasets have been released, such as FrieHAND [8] and GANerated Hands [9] , there is only one available dataset, namely, STB [11] , for stereo sensors.  ... 
doi:10.1109/access.2021.3105969 fatcat:3zmflh7mzbflvpn5au5zksxod4

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images [article]

Christian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan Russell, Max Argus, Thomas Brox
2019 arXiv   pre-print
Estimating 3D hand pose from single RGB images is a highly ambiguous problem that relies on an unbiased training dataset.  ...  For annotating this real-world dataset, we propose an iterative, semi-automated 'human-in-the-loop' approach, which includes hand fitting optimization to infer both the 3D pose and shape for each sample  ...  Moreover, we are able to train a network for full 3D hand shape estimation from a single RGB image.  ... 
arXiv:1909.04349v3 fatcat:b23hq75sn5f6lgleuf4roeznk4

Whole-Body Human Pose Estimation in the Wild [article]

Sheng Jin, Lumin Xu, Jin Xu, Can Wang, Wentao Liu, Chen Qian, Wanli Ouyang, Ping Luo
2020 arXiv   pre-print
Extensive experiments show that COCO-WholeBody not only can be used to train deep models from scratch for whole-body pose estimation but also can serve as a powerful pre-training dataset for many different  ...  tasks such as facial landmark detection and hand keypoint estimation.  ...  Mueller, F., Bernard, F., Sotnychenko, O., Mehta, D., Sridhar, S., Casas, D., Theobalt, C.: Ganerated hands for real-time 3d hand tracking from monocular rgb.  ... 
arXiv:2007.11858v1 fatcat:rwjd2cwbovhgvd5ifz3cqw2ihy

Deep learning based sign language recognition [article]

Maria Parelli, National Technological University Of Athens
2021
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 49–59. https://doi.org/10.1109/CVPR.2018.00013 [38] Niu  ...  Thus, recent works focus mostly on 3D hand pose estimation from monocular RGB im- ages.  ... 
doi:10.26240/heal.ntua.21907 fatcat:ipz5aai2mzfblkemusxceynipe