A 3D shape descriptor for human pose recovery

被引：0

作者：

Gond, Laetitia ^{[1
]}

Sayd, Patrick ^{[1
]}

Chateau, Thierry ^{[2
]}

Dhome, Michel ^{[2
]}

机构：

[1] CEA, LIST, Lab Syst Vis Embarques, Boite Courrier 94, F-91191 Gif Sur Yvette, France

[2] Univ Blaise Pascal, CNRS, LASMEA, Clermont Ferrand, France

来源：

ARTICULATED MOTION AND DEFORMABLE OBJECTS, PROCEEDINGS | 2008年 / 5098卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper deals with human body pose recovery through a multicamera system, which is a key task in monitoring of human activity. The proposed algorithm reconstructs the 3D visual hull of the observed body and characterizes its shape with a new 3D shape descriptor. The body pose is then infered through an original two-stage regression process. As the learning step is independant of the camera configuration, the resulting system is easy to set up. This solution is evaluated on synthetic scenes and promising results on real images are also presented.

引用

页码：370 / +

页数：2

共 50 条

[41] Preface to the Special Issue on Human Pose, Motion, Activities and Shape in 3D
Manuel J. Marín-Jiménez
Javier Romero
Hao Li
Grégory Rogez
International Journal of Computer Vision, 2022, 130 : 199 - 200
[42] Sequential 3D Human Pose and Shape Estimation from Point Clouds
Wang, Kangkan
Xie, Jin
Zhang, Guofeng
Liu, Lei
Yang, Jian
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 7273 - 7282
[43] LEAPSE: Learning Environment Affordances for 3D Human Pose and Shape Estimation
Tian, Fangzheng
Kim, Sungchan
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 3285 - 3300
[44] EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild
Kaufmann, Manuel
Song, Jie
Guo, Chen
Shen, Kaiyue
Jiang, Tianjian
Tang, Chengcheng
Zarate, Juan Jose
Hilliges, Otmar
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 14586 - 14597
[45] imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose
Alldieck, Thiemo
Xu, Hongyi
Sminchisescu, Cristian
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 5441 - 5450
[46] A multiresolution descriptor for deformable 3D shape retrieval
Li, Chunyuan
Ben Hamza, A.
VISUAL COMPUTER, 2013, 29 (6-8) : 513 - 524
[47] Personalized Graph Generation for Monocular 3D Human Pose and Shape Estimation
Hu, Junxing
Zhang, Hongwen
Wang, Yunlong
Ren, Min
Sun, Zhenan
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (04) : 2399 - 2413
[48] Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
Pang, Hui En
Cai, Zhongang
Yang, Lei
Zhang, Tianwei
Liu, Ziwei
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[49] Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence
Xie, Jin
Wang, Meng
Fang, Yi
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3309 - 3317
[50] SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation
Xu, Xiangyu
Liu, Lijuan
Yan, Shuicheng
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (05) : 3275 - 3289

← 1 2 3 4 5 →