Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion

被引:0
|
作者
Amirreza Farnoosh
Sarah Ostadabbas
机构
[1] Northeastern University,Augmented Cognition Lab, Electrical and Computer Engineering Department
来源
关键词
3D skeletal motion; Bayesian inference; Biologically valid interpretation; Generative models; Latent state modeling; Variational inference;
D O I
暂无
中图分类号
学科分类号
摘要
In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We parameterize these temporal processes with regard to a switching deep vector autoregressive prior in order to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses the meaningful intrinsic states in the dynamics of 3D pose data using approximate variational inference, and enables a realistic low-level dynamical generation and segmentation of complex skeleton movements. Our experiments on four biological motion data containing bat flight, salsa dance, walking, and golf datasets substantiate superior performance of our model in comparison with the state-of-the-art methods.
引用
收藏
页码:2695 / 2706
页数:11
相关论文
共 50 条
  • [21] Motion Guided Deep Dynamic 3D Garments
    Zhang, Meng
    Ceylan, Duygu
    Mitra, Niloy J.
    ACM TRANSACTIONS ON GRAPHICS, 2022, 41 (06):
  • [22] A Deep Emulator for Secondary Motion of 3D Characters
    Zheng, Mianlun
    Zhou, Yi
    Ceylan, Duygu
    Barbic, Jernej
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 5928 - 5936
  • [23] A deep generative model of 3D single-cell organization
    Donovan-Maiye, Rory M.
    Brown, Jackson M.
    Chan, Caleb K.
    Ding, Liya
    Yan, Calysta
    Gaudreault, Nathalie
    Theriot, Julie A.
    Maleckar, Mary M.
    Knijnenburg, Theo A.
    Johnson, Gregory R.
    PLOS COMPUTATIONAL BIOLOGY, 2022, 18 (01)
  • [24] DEEP GENERATIVE FRAMEWORK FOR INTERACTIVE 3D TERRAIN AUTHORING AND MANIPULATION
    Naik, Shanthika
    Jain, Aryamaan
    Sharma, Avinash
    Rajan, K. S.
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 6410 - 6413
  • [25] Dynamical Binary Latent Variable Models for 3D Human Pose Tracking
    Taylor, Graham W.
    Sigal, Leonid
    Fleet, David J.
    Hinton, Geoffrey E.
    2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, : 631 - 638
  • [26] Enhancing cryo-EM maps with 3D deep generative networks for assisting protein structure modeling
    Subramaniya, Sai Raghavendra Maddhuri Venkata
    Terashi, Genki
    Kihara, Daisuke
    BIOINFORMATICS, 2023, 39 (08)
  • [27] 3D modeling of human hand with motion constraints
    Yasumuro, Y
    Chen, Q
    Chihara, K
    INTERNATIONAL CONFERENCE ON RECENT ADVANCES IN 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, 1997, : 275 - 282
  • [28] 3D Tree Modeling using Motion Capture
    Long, Jie
    Jones, Michael D.
    2012 IEEE FOURTH INTERNATIONAL SYMPOSIUM ON PLANT GROWTH MODELING, SIMULATION, VISUALIZATION AND APPLICATIONS (PMA), 2012, : 242 - 249
  • [29] 3D modeling and motion parallax for improved videoconferencing
    Zhe Zhu
    Ralph R.Martin
    Robert Pepperell
    Alistair Burleigh
    Computational Visual Media, 2016, 2 (02) : 131 - 142
  • [30] 3D modeling and motion parallax for improved videoconferencing
    Zhu Z.
    Martin R.R.
    Pepperell R.
    Burleigh A.
    Computational Visual Media, 2016, 2 (2) : 131 - 142