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
  • [31] DLGAN: Depth-Preserving Latent Generative Adversarial Network for 3D Reconstruction
    Liu, Caixia
    Kong, Dehui
    Wang, Shaofan
    Li, Jinghua
    Yin, Baocai
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 2843 - 2856
  • [32] Physically-aware Generative Network for 3D Shape Modeling
    Mezghanni, Mariem
    Boulkenafed, Malika
    Lieutier, Andre
    Ovsjanikov, Maks
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 9326 - 9337
  • [33] Evolutive 3D Modeling: A Proposal for a New Generative Design Methodology
    Nebot, Jaime
    Pena, Juan A.
    Lopez Gomez, Carmelo
    SYMMETRY-BASEL, 2021, 13 (02): : 1 - 12
  • [34] HOLOFUSION: Towards Photo-realistic 3D Generative Modeling
    Karnewar, Animesh
    Mitra, Niloy J.
    Vedaldi, Andrea
    Novotny, David
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 22919 - 22928
  • [35] Generative tracking of 3D human motion by hierarchical annealed genetic algorithm
    Zhao, Xu
    Liu, Yuncai
    PATTERN RECOGNITION, 2008, 41 (08) : 2470 - 2483
  • [36] Modeling skeletal muscle disorders in engineered 3D cultures
    Rekersbrink, T.
    Zschuentzsch, J.
    Zimmermann, W. H.
    Schmidt, J.
    Tiburcy, M.
    NAUNYN-SCHMIEDEBERGS ARCHIVES OF PHARMACOLOGY, 2018, 391 : S42 - S42
  • [37] GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors
    Dong, Yuan
    Zuo, Qi
    Gu, Xiaodong
    Yuan, Weihao
    Zhao, Zhengyi
    Dong, Zilong
    Bo, Liefeng
    Huang, Qixing
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024, 2024, : 56 - 66
  • [38] MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation
    Han, Kun
    Xiong, Yifeng
    You, Chenyu
    Khosravi, Pooya
    Sun, Shanlin
    Yan, Xiangyi
    Duncan, James S.
    Xie, Xiaohui
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2023, PT I, 2023, 14220 : 759 - 769
  • [39] Deep Motion Network for Freehand 3D Ultrasound Reconstruction
    Luo, Mingyuan
    Yang, Xin
    Wang, Hongzhang
    Du, Liwei
    Ni, Dong
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT IV, 2022, 13434 : 290 - 299
  • [40] ASMNet: Action and Style-Conditioned Motion Generative Network for 3D Human Motion Generation
    Li, Zongying
    Wang, Yong
    Du, Xin
    Wang, Can
    Koch, Reinhard
    Liu, Mengyuan
    CYBORG AND BIONIC SYSTEMS, 2024, 5