Filters








3,629 Hits in 7.9 sec

Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation [article]

Samira Kaviani, Amir Rahimi, Richard Hartley
2021
To tackle this issue in the context of semi-supervised 3D hand shape and pose estimation, we propose the Pose Alignment network to propagate 3D annotations from labelled frames to nearby unlabelled frames  ...  We show that incorporating the alignment supervision on pairs of labelled-unlabelled frames allows us to improve the pose estimation accuracy.  ...  The checkmarks show that the methods include 6D object pose estimation. 7 1 4 Fig. 1 . 41 Fig. 1. Overview of our framework for semi-supervised 3D hand pose and shape prediction.  ... 
doi:10.48550/arxiv.2111.15199 fatcat:5c6ndvux3fhjrjzfnm7k7kdriq

Monocular 3D Human Pose Estimation with a Semi-supervised Graph-Based Method

Mahdieh Abbasi, Hamid R. Rabiee, Christian Gagne
2015 2015 International Conference on 3D Vision  
In this paper, a semi-supervised graph-based method for estimating 3D body pose from a sequence of silhouettes, is presented.  ...  Furthermore, by exploiting the relationships between labeled and unlabeled data, the proposed method can estimate the 3D body poses, with a small set of labeled data.  ...  On one hand, generative approaches require a 3D human body model with parameters such as 3D joint angles, 3D joint positions, and 3D shapes, which constitutes the parameter space.  ... 
doi:10.1109/3dv.2015.64 dblp:conf/3dim/AbbasiRG15 fatcat:si3an5t66bdt3hgiveqvpmsbry

Joint Affinity Propagation for Multiple View Segmentation

Jianxiong Xiao, Jingdong Wang, Ping Tan, Long Quan
2007 2007 IEEE 11th International Conference on Computer Vision  
Third, a semi-supervised affinity propagation algorithm is proposed to refine the automatic results with the user assistance.  ...  Then, we propose a hierarchical sparse affinity propagation algorithm to automatically and jointly segment 2D images and group 3D points.  ...  Acknowledgements The work is supported by Hong Kong RGC projects 619005, 619006 and 619107, and NSFC/RGC Joint Grant N-HKUST602/05.  ... 
doi:10.1109/iccv.2007.4408928 dblp:conf/iccv/XiaoWTQ07 fatcat:pahxtrvjjjdczhx5zxeyjqpy2y

3D Object Structure Recovery via Semi-supervised Learning on Videos

Qian He, Desen Zhou, Xuming He
2018 British Machine Vision Conference  
In this work, we propose a semi-supervised learning strategy to build a robust 3D object interpreter, which exploits rich object videos for better generalization under large pose variations and noisy 2D  ...  This paper addresses the problem of joint 3D object structure and camera pose estimation from a single RGB image.  ...  Our semi-supervised learning strategy allows the 2D-to-3D module to cope with the inaccurate 2D estimations in a more robust manner and thus produces better 3D predictions.  ... 
dblp:conf/bmvc/HeZH18 fatcat:djlnrdjtorattfv5in2rtisho4

Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels [article]

L. Koestler and N. Yang and R. Wang and D. Cremers
2020 arXiv   pre-print
The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling.  ...  We propose a network architecture and training procedure for learning monocular 3D object detection without 3D bounding box labels.  ...  This work has been presented at the German Conference for Pattern Recognition (GCPR) 2020 and the final paper will be published in LNCS (Springer).  ... 
arXiv:2010.03506v1 fatcat:mrqr2gth4nhurjrcl7bjqzk7kq

Dual Grid Net: hand mesh vertex regression from single depth maps [article]

Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
2019 arXiv   pre-print
We present a method for recovering the dense 3D surface of the hand by regressing the vertex coordinates of a mesh model from a single depth map.  ...  With multi-camera rig during training to resolve self-occlusion, it can perform competitively with strongly supervised methods Without any human annotation.  ...  Introduction We consider the problem of estimating the 3D object shape and pose from single depth images.  ... 
arXiv:1907.10695v1 fatcat:67ln42zlujf73kgiwddedplruu

Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset [article]

Yang Fu, Xiaolong Wang
2022 arXiv   pre-print
We utilize this data to generalize category-level 6D object pose estimation in the wild with semi-supervised learning.  ...  Project page with Wild6D data: https://oasisyang.github.io/semi-pose .  ...  The RePoNet is composed of two branches of networks with a Pose Network to estimate the 6D object pose and a Shape Network to estimate the 3D object shape.  ... 
arXiv:2206.15436v1 fatcat:qygwkazj7vetbpa25qj4mwx3te

Learning Pose Specific Representations by Predicting Different Views

Georg Poier, David Schinagl, Horst Bischof
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
That is, given only the pose and shape parameters of a hand, the hand's appearance from any viewpoint can be approximated.  ...  Moreover, when training the proposed method jointly with labeled and unlabeled data, it consistently surpasses the performance of its fully supervised counterpart, while reducing the amount of needed labeled  ...  for manually labeling hand poses.  ... 
doi:10.1109/cvpr.2018.00014 dblp:conf/cvpr/PoierSB18 fatcat:iwsnpeyhj5gsrapwqzivokqicu

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding [article]

Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, Kui Jia
2021 arXiv   pre-print
In this work, we present a 3D AffordanceNet dataset, a benchmark of 23k shapes from 23 semantic object categories, annotated with 18 visual affordance categories.  ...  In addition we also investigate a semi-supervised learning setup to explore the possibility to benefit from unlabeled data.  ...  The words Full-Shape and VAT represent full-shape estimation and semi-supervised affordance estimation with virtual adversarial training. Wrap. is the abbreviation of Wrap-Grasp.  ... 
arXiv:2103.16397v2 fatcat:5iqpr46jbndmjkw3b46hymbaku

Hand Pose Estimation through Semi-Supervised and Weakly-Supervised Learning [article]

Natalia Neverova, Christian Wolf, Florian Nebout, Graham Taylor
2017 arXiv   pre-print
We propose a method for hand pose estimation based on a deep regressor trained on two different kinds of input.  ...  The mapping from raw depth to segmentation maps is learned in a semi/weakly-supervised way from two different datasets: (i) a synthetic dataset created through a rendering pipeline including densely labeled  ...  Taylor acknowledges the support of NSERC, CFI, and NVIDIA.  ... 
arXiv:1511.06728v4 fatcat:r4jbkd6poffs3h2ow6xmou4ej4

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Workshop: Automated Pose Estimation in 3D Point Clouds Applying Annealing Particle Filters and Inverse Kinematics on a GPU Leistner, Christian Online Multi-Class LPBoost On-line Semi-supervised Multiple-Instance  ...  Object and Human Pose in Human-Object Interaction Activities Connecting Modalities: Semi-supervised Segmentation and Annotation of Images Using Unaligned Text Corpora Felzenszwalb, Pedro F.  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Learning Pose Specific Representations by Predicting Different Views [article]

Georg Poier, David Schinagl, Horst Bischof
2018 arXiv   pre-print
That is, given only the pose and shape parameters of a hand, the hand's appearance from any viewpoint can be approximated.  ...  Moreover, when training the proposed method jointly with labeled and unlabeled data, it consistently surpasses the performance of its fully supervised counterpart, while reducing the amount of needed labeled  ...  the dataset, and Anna Micheler-Hofer, Stefan Ainetter and Florian Ziessler for manually labeling hand poses.  ... 
arXiv:1804.03390v2 fatcat:3fxeyrxgbfbwtd2nu2gon7cuzy

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective [article]

Wu Liu, Qian Bao, Yu Sun, Tao Mei
2021 arXiv   pre-print
We believe this survey will provide the readers with a deep and insightful understanding of monocular human pose estimation.  ...  Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications.  ...  Moreover, with the rapid development of 3D pose and shape estimation, it is necessary to have a deeper survey on the human pose estimation from 2D to 3D.  ... 
arXiv:2104.11536v1 fatcat:tdag2jq2vjdrjekwukm5nu7l6a

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.  ...  Discriminative approaches: Weakly-supervised and semi-supervised learning The increased number of real-world datasets with complete 3D annotations has been attributed to the fast growth of 3D hand shape  ... 
doi:10.1016/j.vrih.2021.05.002 fatcat:4tbhftt3ira6fporaqlscqhsse

Appearance Consensus Driven Self-Supervised Human Mesh Recovery [article]

Jogendra Nath Kundu, Mugalodi Rakesh, Varun Jampani, Rahul Mysore Venkatesh, R. Venkatesh Babu
2020 arXiv   pre-print
We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks at comparable supervision levels.  ...  We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision.  ...  Note that at test time, we perform single image inference to estimate 3D human pose and shape.  ... 
arXiv:2008.01341v1 fatcat:jyqhw3pwjrcxxpozwetd36r6ay
« Previous Showing results 1 — 15 out of 3,629 results