Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes

Author:

Choi Hongsuk1,Moon Gyeongsik1,Park JoonKyu1,Lee Kyoung Mu1

Affiliation:

1. Seoul National University,Dept. of ECE & ASRI,Korea

Funder

IITP

Seoul National University

Publisher

IEEE

Reference53 articles.

1. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image

2. Automatic differentiation in pytorch;paszke;NeurIPS,0

3. Pose2pose: 3D positional pose-guided 3D rotational pose prediction for expressive 3d human pose and mesh estimation;moon;ArXiv Preprint,2020

4. NeuralAnnot: Neural annotator for in-the-wild expressive 3D human pose and mesh training sets;moon;ArXiv Preprint,2020

5. I2L-MeshNet: Image-to-Lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image;moon;ECCV,0

Cited by 43 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Confidence sharing adaptation for out-of-domain human pose and shape estimation;Computer Vision and Image Understanding;2024-09

2. Deep learning for 3D human pose estimation and mesh recovery: A survey;Neurocomputing;2024-09

3. Action-conditioned contrastive learning for 3D human pose and shape estimation in videos;Computer Vision and Image Understanding;2024-09

4. A Survey of 3D Human Body Reconstruction from Single and Multiple Camera Views;International Journal of Image and Graphics;2024-08-22

5. Visibility-Aware Human Mesh Recovery via Balancing Dense Correspondence and Probability Model;2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW);2024-07-15

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3