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
  • [1] Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion
    Farnoosh, Amirreza
    Ostadabbas, Sarah
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (11) : 2695 - 2706
  • [2] 3DILG: Irregular Latent Grids for 3D Generative Modeling
    Zhang, Biao
    Niessner, Matthias
    Wonka, Peter
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [3] Generative tracking of 3D human motion in latent space by sequential clonal selection algorithm
    Yi Li
    Zhengxing Sun
    Multimedia Tools and Applications, 2014, 69 : 79 - 109
  • [4] Generative tracking of 3D human motion in latent space by sequential clonal selection algorithm
    Li, Yi
    Sun, Zhengxing
    MULTIMEDIA TOOLS AND APPLICATIONS, 2014, 69 (01) : 79 - 109
  • [5] Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
    Wu, Jiajun
    Zhang, Chengkai
    Xue, Tianfan
    Freeman, William T.
    Tenenbaum, Joshua B.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
  • [6] Deep generative models for 3D molecular structure
    Baillif, Benoit
    Cole, Jason
    McCabe, Patrick
    Bender, Andreas
    CURRENT OPINION IN STRUCTURAL BIOLOGY, 2023, 80
  • [7] Deep Generative Models for 3D Linker Design
    Imrie, Fergus
    Bradley, Anthony R.
    van der Schaar, Mihaela
    Deane, Charlotte M.
    JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2020, 60 (04) : 1983 - 1995
  • [8] Deep generative design with 3D pharmacophoric constraints
    Imrie, Fergus
    Hadfield, Thomas E.
    Bradley, Anthony R.
    Deane, Charlotte M.
    CHEMICAL SCIENCE, 2021, 12 (43) : 14577 - 14589
  • [9] Interactive 3D Modeling with a Generative Adversarial Network
    Liu, Jerry
    Yu, Fisher
    Funkhouser, Thomas
    PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2017, : 126 - 134
  • [10] 3D Generative Model Latent Disentanglement via Local Eigenprojection
    Foti, Simone
    Koo, Bongjin
    Stoyanov, Danail
    Clarkson, Matthew J.
    COMPUTER GRAPHICS FORUM, 2023, 42 (06)