Reconstructing Articulated Rigged Models from RGB-D Videos

被引:16
|
作者
Tzionas, Dimitrios [1 ,2 ]
Gall, Juergen [1 ]
机构
[1] Univ Bonn, Bonn, Germany
[2] MPI Intelligent Syst, Tubingen, Germany
关键词
Kinematic model learning; Skeletonization; Rigged model acquisition; Deformable tracking; Spectral clustering; Mean curvature flow; MOTION;
D O I
10.1007/978-3-319-49409-8_53
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consists of a watertight mesh, embedded skeleton, and skinning weights.
引用
收藏
页码:620 / 633
页数:14
相关论文
共 50 条
  • [1] Reconstructing 3D Contour Models of General Scenes from RGB-D Sequences
    Wang, Weiran
    Di, Huijun
    Song, Lingxiao
    [J]. MULTIMEDIA MODELING, MMM 2022, PT II, 2022, 13142 : 158 - 170
  • [2] Visual Recognition in RGB Images and Videos by Learning from RGB-D Data
    Li, Wen
    Chen, Lin
    Xu, Dong
    Van Gool, Luc
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (08) : 2030 - 2036
  • [3] Estimating Spatial Layout of Rooms from RGB-D Videos
    Wang, Anran
    Lu, Jiwen
    Cai, Jianfei
    Wang, Gang
    Cham, Tat-Jen
    [J]. 2014 IEEE 16TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2014,
  • [4] Recognition and Classification of Human Activity from RGB-D Videos
    Gurkaynak, Deniz
    Yalcin, Hulya
    [J]. 2015 23RD SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2015, : 1745 - 1748
  • [5] ACTION RECOGNITION IN RGB-D EGOCENTRIC VIDEOS
    Tang, Yansong
    Tian, Yi
    Lu, Jiwen
    Feng, Jianjiang
    Zhou, Jie
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3410 - 3414
  • [6] Learning human activities and object affordances from RGB-D videos
    Koppula, Hema Swetha
    Gupta, Rudhir
    Saxena, Ashutosh
    [J]. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2013, 32 (08): : 951 - 970
  • [7] Fall Detection in RGB-D Videos for Elderly Care
    Yun, Yixiao
    Innocenti, Christopher
    Nero, Gustav
    Linden, Henrik
    Gu, Irene Yu-Hua
    [J]. 2015 17TH INTERNATIONAL CONFERENCE ON E-HEALTH NETWORKING, APPLICATION & SERVICES (HEALTHCOM), 2015, : 422 - 427
  • [8] Generative adversarial networks for generating RGB-D videos
    Nakahira, Yuki
    Kawamoto, Kazuhiko
    [J]. 2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 1276 - 1281
  • [9] A posture measurement approach for an articulated manipulator by RGB-D cameras
    Shi, Haobin
    Xu, Meng
    Hwang, Kao-Shing
    Hung, Chia-Hung
    [J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2019, 16 (02)
  • [10] Reconstructing 3D Human Pose from RGB-D Data with Occlusions
    Dang, Bowen
    Zhao, Xi
    Zhang, Bowen
    Wang, He
    [J]. COMPUTER GRAPHICS FORUM, 2023, 42 (07)