Filters








53 Hits in 10.5 sec

Hand Pose Estimation via Latent 2.5D Heatmap Regression [chapter]

Umar Iqbal, Pavlo Molchanov, Thomas Breuel, Juergen Gall, Jan Kautz
2018 Lecture Notes in Computer Science  
In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation.  ...  Estimating the 3D pose of a hand is an essential part of human-computer interaction.  ...  Direct 2.5D Heatmap Regression Heatmap regression is the de-facto approach for 2D pose estimation [26, 27, 59, 60] .  ... 
doi:10.1007/978-3-030-01252-6_8 fatcat:v3qp4leaire3ra2bywz7z5ab7y

Hand Pose Estimation via Latent 2.5D Heatmap Regression [article]

Umar Iqbal, Pavlo Molchanov, Thomas Breuel, Juergen Gall, Jan Kautz
2018 arXiv   pre-print
In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation.  ...  Estimating the 3D pose of a hand is an essential part of human-computer interaction.  ...  Heatmap regression is now a standard approach for 2D pose estimation since it allows to accurately localize the keypoints in the image via per-pixel predictions.  ... 
arXiv:1804.09534v1 fatcat:aroxdzw3tvbtze5og3ut744hpu

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation [article]

Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black, Otmar Hilliges
2021 arXiv   pre-print
Due to the homogeneous appearance of hands, this makes estimating the 3D pose of interacting hands from images difficult.  ...  Motivated by this insight, we propose DIGIT, a novel method for estimating the 3D poses of two interacting hands from a single monocular image.  ...  Interacting hand pose estimation. To estimate the final 3D hand pose of both hands, we learn a function F : F → P 2.5D that maps the fused feature map F to 2.5D pose.  ... 
arXiv:2107.00434v2 fatcat:frrzchccbja4pclwkh4ebhposi

Learning To Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation

Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black, Otmar Hilliges
2021 2021 International Conference on 3D Vision (3DV)  
When estimating the 3D pose of interacting hands, state-of-the-art methods struggle to disambiguate the appearance of the two hands and their parts.  ...  Our model, DIGIT, reduces the ambiguity by predicting and leveraging a probabilistic part segmentation volume (2.1) to produce reliable pose estimates even when the two hands are in direct contact and  ...  Inspired by [20] , our pose estimator predicts the latent 2D heatmap H * 2D ∈ IR WF×HF×2J for the 2D joint locations and the latent rootrelative depth map H * z ∈ IR WF×HF×2J for the root-relative depth  ... 
doi:10.1109/3dv53792.2021.00011 fatcat:l6ozyteqv5dixa7x6vfgnponpq

Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild

Umar Iqbal, Pavlo Molchanov, Jan Kautz
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses.  ...  Since multi-view consistency is prone to degenerated solutions, we adopt a 2.5D pose representation and propose a novel objective function that can only be minimized when the predictions of the trained  ...  To this end, we adopt the 2.5D heatmap regression approach of [12] .  ... 
doi:10.1109/cvpr42600.2020.00529 dblp:conf/cvpr/IqbalMK20 fatcat:wmjxjjxm7fce7gc6oe7nj25f2y

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild [article]

Umar Iqbal and Pavlo Molchanov and Jan Kautz
2020 arXiv   pre-print
One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses.  ...  Since multi-view consistency is prone to degenerated solutions, we adopt a 2.5D pose representation and propose a novel objective function that can only be minimized when the predictions of the trained  ...  To this end, we adopt the 2.5D heatmap regression approach of [12] .  ... 
arXiv:2003.07581v1 fatcat:ovvms7wlojeihpbq3mzthzswlq

HANDS18: Methods, Techniques and Applications for Hand Observation [article]

Iason Oikonomidis, Guillermo Garcia-Hernando, Angela Yao, Antonis Argyros, Vincent Lepetit, Tae-Kyun Kim
2018 arXiv   pre-print
Topics of the submitted works and invited talks and posters included novel methods for hand pose estimation from RGB, depth, or skeletal data, datasets for special cases and real-world applications, and  ...  techniques for hand motion re-targeting and hand gesture recognition.  ...  IP4: "Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network" [37] . IP5: "Hand Pose Estimation via Latent 2.5D Heatmap Regression" [18] .  ... 
arXiv:1810.10818v1 fatcat:vzisj4v7cractmpj3az4n6fefa

HANDS18: Methods, Techniques and Applications for Hand Observation [chapter]

Iason Oikonomidis, Guillermo Garcia-Hernando, Angela Yao, Antonis Argyros, Vincent Lepetit, Tae-Kyun Kim
2019 Lecture Notes in Computer Science  
Topics of the submitted works and invited talks and posters included novel methods for hand pose estimation from RGB, depth, or skeletal data, datasets for special cases and real-world applications, and  ...  techniques for hand motion re-targeting and hand gesture recognition.  ...  IP4: "Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network" [37] . IP5: "Hand Pose Estimation via Latent 2.5D Heatmap Regression" [18] .  ... 
doi:10.1007/978-3-030-11024-6_20 fatcat:diga4cihnvfjhk2qqsim5w7bvm

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

Ziwei Yu, Linlin Yang, Shicheng Chen, Angela Yao
2021 arXiv   pre-print
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.  ...  This paper addresses the 3D point cloud reconstruction and 3D pose estimation of the human hand from a single RGB image.  ...  Hand pose estimation via latent 2.5 d heatmap regression.  ... 
arXiv:2112.06389v1 fatcat:n6zujacknrfqllnld4vaulia5m

Aligning Latent Spaces for 3D Hand Pose Estimation

Linlin Yang, Shile Li, Dongheui Lee, Angela Yao
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Hand pose estimation from monocular RGB inputs is a highly challenging task.  ...  In this work, we propose to learn a joint latent representation that leverages other modalities as weak labels to improve RGB-based hand pose estimation.  ...  [31] regress heatmaps for each hand keypoint from RGB images and then regress the 3D hand pose from these heatmaps with fully-connected layers. Mueller et al.  ... 
doi:10.1109/iccv.2019.00242 dblp:conf/iccv/YangLLY19 fatcat:tymbevymqraypfzhvii34awpsi

RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images [article]

Shanxin Yuan, Bjorn Stenger, Tae-Kyun Kim
2018 arXiv   pre-print
During testing, when only an RGB image is available, our method produces accurate 3D hand pose predictions. Our method is also tested on 2D hand pose estimation.  ...  Experiments on three public datasets show that the method outperforms the state-of-the-art methods for hand pose estimation using RGB image input.  ...  Absolute 3D hand poses are reconstructed from the latent 2.5D heatmaps. Cai et al.  ... 
arXiv:1811.07376v1 fatcat:lrfsih64arccxfsgn37duwvjbq

3D Hand Pose and Shape Estimation from RGB Images for Improved Keypoint-Based Hand-Gesture Recognition [article]

Danilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Adriano Fragomeni, Daniele Pannone
2021 arXiv   pre-print
presented method is an effective solution able to generate stable 3D estimates for the hand pose and shape.  ...  Estimating the 3D hand pose from a 2D image is a well-studied problem and a requirement for several real-life applications such as virtual reality, augmented reality, and hand-gesture recognition.  ...  ., 2D heatmaps, allowing the network to estimate the 3D pose via symmetric streams and to analyze the prior pose and the latent pose representation derived by the network.  ... 
arXiv:2109.13879v1 fatcat:zakt32k6frfk5lczohpun5hski

Hand Pose Estimation: A Survey [article]

Bardia Doosti
2019 arXiv   pre-print
Hand Pose Estimation a hot topic in computer vision field.  ...  To the best of our knowledge this is the most complete list of all the datasets in the hand pose estimation field.  ...  To estimate hand pose via depth maps, it is needed to train the model to produce the same pose for different depth map inputs.  ... 
arXiv:1903.01013v2 fatcat:rqkthrt4mjawlk4p2ij5nut64q

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.  ...  Instead of directly regressing 3D hand poses from an estimated 2D heatmap that tends to lose detailed spatial information, Iqbal et al.  ... 
doi:10.1016/j.vrih.2021.05.002 fatcat:4tbhftt3ira6fporaqlscqhsse

Dense 3D Regression for Hand Pose Estimation [article]

Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
2017 arXiv   pre-print
We present a simple and effective method for 3D hand pose estimation from a single depth frame.  ...  As opposed to previous state-of-the-art methods based on holistic 3D regression, our method works on dense pixel-wise estimation.  ...  To that end, we propose a combined pixel-wise detection and dense regression method for hand pose estimation.  ... 
arXiv:1711.08996v1 fatcat:yxc5hlmcc5f33hh6j7s4ftzoqm
« Previous Showing results 1 — 15 out of 53 results