Physics-based Scene Layout Generation from Human Motion

被引:0
|
作者
Li, Jianan [1 ,2 ]
Huang, Tao [1 ]
Zhu, Qingxu [2 ]
Wong, Tien-Tsin [1 ]
机构
[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[2] Tencent Robot X, Shenzhen, Peoples R China
关键词
Scene layout generation; physics-based character control; reinforcement learning;
D O I
10.1145/3641519.3657517
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Creating scenes for captured motions that achieve realistic human-scene interaction is crucial for 3D animation in movies or video games. As character motion is often captured in a blue-screened studio without real furniture or objects in place, there may be a discrepancy between the planned motion and the captured one. This gives rise to the need for automatic scene layout generation to relieve the burdens of selecting and positioning furniture and objects. Previous approaches cannot avoid artifacts like penetration and floating due to the lack of physical constraints. Furthermore, some heavily rely on specific data to learn the contact affordances, restricting the generalization ability to different motions. In this work, we present a physics-based approach that simultaneously optimizes a scene layout generator and simulates a moving human in a physics simulator. To attain plausible and realistic interaction motions, our method explicitly introduces physical constraints. To automatically recover and generate the scene layout, we minimize the motion tracking errors to identify the objects that can afford interaction. We use reinforcement learning to perform a dual-optimization of both the character motion imitation controller and the scene layout generator. To facilitate the optimization, we reshape the tracking rewards and devise pose prior guidance obtained from our estimated pseudo-contact labels. We evaluate our method using motions from SAMP and PROX, and demonstrate physically plausible scene layout reconstruction compared with the previous kinematics-based method.
引用
收藏
页数:10
相关论文
共 50 条
  • [41] Modelling Nonlinear Site Effects in Physics-Based Ground Motion Simulation
    de la Torre, Christopher A.
    Bradley, Brendon A.
    GEOTECHNICAL EARTHQUAKE ENGINEERING AND SOIL DYNAMICS V: SEISMIC HAZARD ANALYSIS, EARTHQUAKE GROUND MOTIONS, AND REGIONAL-SCALE ASSESSMENT, 2018, (291): : 514 - 522
  • [42] Spatial Correlations in CyberShake Physics-Based Ground-Motion Simulations
    Chen, Yilin
    Baker, Jack W.
    BULLETIN OF THE SEISMOLOGICAL SOCIETY OF AMERICA, 2019, 109 (06) : 2447 - 2458
  • [43] Multi-Goal Motion Planning with Physics-based Game Engines
    Edelkamp, Stefan
    Plaku, Erion
    2014 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG), 2014,
  • [44] Randomized Physics-Based Motion Planning for Grasping in Cluttered and Uncertain Environments
    Muhayyuddin
    Moll, Mark
    Kavraki, Lydia
    Rosell, Jan
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (02): : 712 - 719
  • [45] AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
    Peng, Xue Bin
    Ma, Ze
    Abbeel, Pieter
    Levine, Sergey
    Kanazawa, Angjoo
    ACM TRANSACTIONS ON GRAPHICS, 2021, 40 (04):
  • [46] A suite of broadband physics-based ground motion simulations for the Istanbul region
    Zhang, Wenyang
    Crempien, Jorge G. F.
    Kurtulus, Asli
    Chen, Peng-Yu
    Arduino, Pedro
    Taciroglu, Ertugrul
    EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS, 2023, 52 (04): : 1161 - 1181
  • [47] Physics-Based Characters
    Hertzmann, Aaron
    Zordan, Victor
    IEEE COMPUTER GRAPHICS AND APPLICATIONS, 2011, 31 (04) : 20 - 21
  • [48] Seismic fragility curves with unconventional ground motion intensity measures from physics-based simulations
    Franco, I. E. Monsalvo
    Smerzini, C.
    Rosti, A.
    Rota, M.
    Paolucci, R.
    Penna, A.
    BULLETIN OF EARTHQUAKE ENGINEERING, 2025, : 1885 - 1915
  • [49] Physics-Based Motion Control Through DRL's Reward Functions
    Sousa, Antonio S.
    Nunes, Rubens F.
    Vidal, Creto A.
    Cavalcante-Neto, Joaquim B.
    da Silva, Danilo B.
    PROCEEDINGS OF SYMPOSIUM ON VIRTUAL AND AUGMENTED REALITY, SVR 2021, 2021, : 127 - 136
  • [50] Language-Driven Physics-Based Scene Synthesis and Editing via Feature Splatting
    Qiu, Ri-Zhao
    Yang, Ge
    Zeng, Weijia
    Wang, Xiaolong
    COMPUTER VISION - ECCV 2024, PT XLI, 2025, 15099 : 368 - 383