Filters








22,643 Hits in 12.8 sec

Learning to Estimate 3D Human Pose and Shape from a Single Color Image [article]

Georgios Pavlakos, Luyang Zhu, Xiaowei Zhou, Kostas Daniilidis
2018 arXiv   pre-print
This work addresses the problem of estimating the full body 3D human pose and shape from a single color image.  ...  The proposed approach outperforms previous baselines on this task and offers an attractive solution for direct prediction of 3D shape from a single color image.  ...  Acknowledgements: We gratefully appreciate support through the following grants: NSF-IIP-1439681 (I/UCRC), ARL RCTA W911NF-10-2-0016, ONR N00014-17-1-2093, DARPA FLA program and NSF/IUCRC.  ... 
arXiv:1805.04092v1 fatcat:zwnxgnkiergj7l4wn4wclvlb2m

Learning to Estimate 3D Human Pose and Shape from a Single Color Image

Georgios Pavlakos, Luyang Zhu, Xiaowei Zhou, Kostas Daniilidis
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
This work addresses the problem of estimating the full body 3D human pose and shape from a single color image.  ...  The proposed approach outperforms previous baselines on this task and offers an attractive solution for direct prediction of 3D shape from a single color image.  ...  Acknowledgements: We gratefully appreciate support through the following grants: NSF-IIP-1439681 (I/UCRC), ARL RCTA W911NF-10-2-0016, ONR N00014-17-1-2093, DARPA FLA program and NSF/IUCRC.  ... 
doi:10.1109/cvpr.2018.00055 dblp:conf/cvpr/PavlakosZZD18 fatcat:57er4ormjfa6xbj4bhnkvsnjnq

3D Human Shape Reconstruction from a Polarization Image [article]

Shihao Zou, Xinxin Zuo, Yiming Qian, Sen Wang, Chi Xu, Minglun Gong, Li Cheng
2020 arXiv   pre-print
Inspired by the recent advances in human shape estimation from single color images, in this paper, we attempt at estimating human body shapes by leveraging the geometric cues from single polarization images  ...  This paper tackles the problem of estimating 3D body shape of clothed humans from single polarized 2D images, i.e. polarization images.  ...  Acknowledgement This work is supported by the NSERC Discovery Grants, and the University of Alberta-Huawei Joint Innovation Collaboration grants.  ... 
arXiv:2007.09268v1 fatcat:c2trusxcyjfs5i6hf2kac4oetu

Object-Occluded Human Shape and Pose Estimation From a Single Color Image

Tianshu Zhang, Buzhen Huang, Yangang Wang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we focus on the problem of directly estimating the object-occluded human shape and pose from single color images.  ...  Our key idea is to utilize a partial UV map to represent an objectoccluded human body, and the full 3D human shape estimation is ultimately converted as an image inpainting problem.  ...  human shape and pose estimation from single color images.  ... 
doi:10.1109/cvpr42600.2020.00740 dblp:conf/cvpr/ZhangHW20 fatcat:2np64ffvxbbodkxh3mvrmuen6u

CoreUI: Interactive Core Training System with 3D Human Shape [article]

Haoran Xie and Atsushi Watatani and Kazunori Miyata
2021 arXiv   pre-print
To solve this issue, we employ the skinned multi-person linear model of human shape to recover the 3D human pose from 2D images using pose estimation and human mesh recovery approaches.  ...  In order to support the user in maintaining the correct postures from target poses in the training, we adopt 3D human shape estimation for both the target image and input camera video.  ...  User Interface 3D Shape and Pose Estimation To obtain 3D human shape and pose from a single image, the proposed system adopts pose estimation based on OpenPose to realize the bounding box of the human  ... 
arXiv:2106.09196v1 fatcat:ryg432l4xndynbxrf3z7bq3yqa

Human Appearance Transfer

Mihai Zanfir, Alin-Ionut Popa, Andrei Zanfir, Cristian Sminchisescu
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Our solution to this new problem is formulated in terms of a computational pipeline that combines (1) 3d human pose and body shape estimation from monocular images, (2) identifying 3d surface colors elements  ...  Given a single source image and a single target image, each corresponding to different human subjects, wearing different clothing and in different poses, our goal is to photorealistically transfer the  ...  Given a single source and a single target image of a person, each with different appearance, possibly different body shape and pose, the goal is to transfer the appearance of the person in the first image  ... 
doi:10.1109/cvpr.2018.00565 dblp:conf/cvpr/ZanfirPZS18 fatcat:lbnl5wnodnfy3kt3p5ejzcvwnq

DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image [article]

Pengfei Yao, Zheng Fang, Fan Wu, Yao Feng, Jiwei Li
2019 arXiv   pre-print
Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data.  ...  In this paper, we propose to directly regress the 3D human mesh from a single color image using Convolutional Neural Network(CNN).  ...  Human shape and pose estimation Estimating 3D human pose and shape from a single color image is a challenging problem.  ... 
arXiv:1903.10153v3 fatcat:5zwhcm77njdwzhdeuuj4nq6wu4

Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction [article]

Tong He, John Collomosse, Hailin Jin, Stefano Soatto
2020 arXiv   pre-print
We propose Geo-PIFu, a method to recover a 3D mesh from a monocular color image of a clothed person.  ...  in query point encoding, second, to serve as a coarse human shape proxy to regularize the high-resolution mesh and encourage global shape regularity.  ...  Acknowledgment Research supported in part by ONR N00014-17-1-2072, N00014-13-1-034, ARO W911NF-17-1-0304, and Adobe.  ... 
arXiv:2006.08072v2 fatcat:7qbnswptdfapzh2e5bxygvrsgy

LISA: Learning Implicit Shape and Appearance of Hands [article]

Enric Corona, Tomas Hodan, Minh Vo, Francesc Moreno-Noguer, Chris Sweeney, Richard Newcombe, Lingni Ma
2022 arXiv   pre-print
The shape, color and pose representations are disentangled by design, allowing to estimate or animate only selected parameters.  ...  We train LISA by minimizing the shape and appearance losses on a large set of multi-view RGB image sequences annotated with coarse 3D poses of the hand skeleton.  ...  Shape and color reconstruction from images Table 2 evaluates the hand models on the task of 3D reconstruction from single and multiple views on the Deep-HandMesh dataset [37] .  ... 
arXiv:2204.01695v1 fatcat:53v7sunsjze6ndb5k2exeqz6x4

Human Pose and Shape Estimation from Single Polarization Images [article]

Shihao Zou, Xinxin Zuo, Sen Wang, Yiming Qian, Chuan Guo, Li Cheng
2022 arXiv   pre-print
This paper focuses on a new problem of estimating human pose and shape from single polarization images.  ...  Inspired by the recent applications in surface normal reconstruction from polarization images, in this paper, we attempt to estimate human pose and shape from single polarization images by leveraging the  ...  That is, we consider the problem of estimating human pose and shape from a single polarization image.  ... 
arXiv:2108.06834v2 fatcat:wn4arcnr3nbpxcesf6r3djn67a

Vision-based human motion analysis: An overview

Ronald Poppe
2007 Computer Vision and Image Understanding  
Markerless vision-based human motion analysis has the potential to provide an inexpensive, non-obtrusive solution for the estimation of body poses.  ...  In this paper, we discuss the characteristics of human motion analysis. We divide the analysis into a modeling and an estimation phase.  ...  The author wishes to thank Dariu Gavrila and the anonymous CVIU reviewers for their valuable comments, and all authors that contributed figures to this overview.  ... 
doi:10.1016/j.cviu.2006.10.016 fatcat:yu64upf3a5gfzosmhv5tc2xpbm

ARCH: Animatable Reconstruction of Clothed Humans

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In contrast, ARCH is a learned pose-aware model that produces detailed 3D rigged full-body human avatars from a single unconstrained RGB image.  ...  In this paper, we propose ARCH (Animatable Reconstruction of Clothed Humans), a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image.  ...  We would like to thank Junbang Liang and Yinghao Huang (Interns at FRL) for their work on dataset creation.  ... 
doi:10.1109/cvpr42600.2020.00316 dblp:conf/cvpr/HuangXL0T20 fatcat:pmq4ncbw7bbpnigrgkiclstqqm

ARCH: Animatable Reconstruction of Clothed Humans [article]

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung
2020 arXiv   pre-print
In contrast, ARCH is a learned pose-aware model that produces detailed 3D rigged full-body human avatars from a single unconstrained RGB image.  ...  In this paper, we propose ARCH (Animatable Reconstruction of Clothed Humans), a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image.  ...  We would like to thank Junbang Liang and Yinghao Huang (Interns at FRL) for their work on dataset creation.  ... 
arXiv:2004.04572v2 fatcat:hu5szk3gh5aglnmh2set5o3lwy

TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell [article]

Hayato Onizuka, Zehra Hayirci, Diego Thomas, Akihiro Sugimoto, Hideaki Uchiyama, Rin-ichiro Taniguchi
2020 arXiv   pre-print
Recovering the 3D shape of a person from its 2D appearance is ill-posed due to ambiguities.  ...  Our proposed PCN allows us to learn the distribution of the TSDF in the tetrahedral volume from a single image in an end-to-end manner.  ...  TSDF fields from ground truth (GT) 3D human body scans; and (3) a new CNN-PCN based hourglass network for end-to-end regression of 3D human body shape from a single color image.  ... 
arXiv:2004.10534v1 fatcat:kjuuvzn7jzekpnpxpf54nkgba4

Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features [article]

Shubhendu Jena, Franck Multon, Adnane Boukhayma
2021 arXiv   pre-print
Given a single input color image, existing graph convolutional network (GCN) based techniques for human shape and pose estimation use a single convolutional neural network (CNN) generated global image  ...  We propose to improve on graph convolution based approaches for human shape and pose estimation from monocular input, using pixel-aligned local image features.  ...  CONCLUSION We presented a method for 3D human shape and pose estimation from a single RGB image.  ... 
arXiv:2111.05319v3 fatcat:q3o3w3cxtfglnbyb7tvfpe62xi
« Previous Showing results 1 — 15 out of 22,643 results