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
  • [31] Physics-based scene-level reasoning for object pose estimation in clutter
    Mitash, Chaitanya
    Boularias, Abdeslam
    Bekris, Kostas
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2022, 41 (06): : 615 - 636
  • [32] LayoutVAE: Stochastic Scene Layout Generation From a Label Set
    Jyothi, Akash Abdu
    Durand, Thibaut
    He, Jiawei
    Sigal, Leonid
    Mori, Greg
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9894 - 9903
  • [33] Generation of broadband spectra from physics-based simulations using stochastic LSTM network
    Sreenath, Vemula
    Sreejaya, K. P.
    Raghukanth, S. T. G.
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 126
  • [34] Scene Synthesis from Human Motion
    Ye, Sifan
    Wang, Yixing
    Li, Jiaman
    Park, Dennis
    Liu, C. Karen
    Xu, Huazhe
    Wu, Jiajun
    PROCEEDINGS SIGGRAPH ASIA 2022, 2022,
  • [35] κ-PMP: Enhancing Physics-based Motion Planners with Knowledge-Based Reasoning
    Muhayyuddin
    Akbari, Aliakbar
    Rosell, Jan
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2018, 91 (3-4) : 459 - 477
  • [36] Pattern-free heliostat field layout optimization using physics-based gradient
    Yang, Seonghyeok
    Lee, Kyungeun
    Lee, Ikjin
    SOLAR ENERGY, 2020, 206 : 722 - 731
  • [37] κ-PMP: Enhancing Physics-based Motion Planners with Knowledge-Based Reasoning
    Aliakbar Muhayyuddin
    Jan Akbari
    Journal of Intelligent & Robotic Systems, 2018, 91 : 459 - 477
  • [38] A Physics-Based Statistical Model for Human Gait Analysis
    Zell, Petrissa
    Rosenhahn, Bodo
    PATTERN RECOGNITION, GCPR 2015, 2015, 9358 : 169 - 180
  • [39] Physics-based character animation and human motor control
    Llobera, Joan
    Charbonnier, Caecilia
    PHYSICS OF LIFE REVIEWS, 2023, 46 : 190 - 219
  • [40] Scattering-aware Holographic PIV with Physics-based Motion Priors
    Qi, Miao
    Heidrich, Wolfgang
    2023 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL PHOTOGRAPHY, ICCP, 2023,