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
  • [1] Physics-based Human Motion Estimation and Synthesis from Videos
    Xie, Kevin
    Wang, Tingwu
    Iqbal, Umar
    Guo, Yunrong
    Fidler, Sanja
    Shkurti, Florian
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 11512 - 11521
  • [2] A survey of physics-based human motion simulation
    Xia, Shihong
    Wei, Yi
    Wang, Zhaoqi
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2010, 47 (08): : 1354 - 1361
  • [3] Physics-based simulation of human motion in flight
    Wei, Yi
    Xia, Shi-Hong
    Wang, Zhao-Qi
    Ruan Jian Xue Bao/Journal of Software, 2008, 19 (12): : 3228 - 3236
  • [4] Motion Generation for Physics-Based Character by Clustering Selection
    Zhang Y.
    Xie W.
    Li S.
    Liu X.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2018, 30 (07): : 1258 - 1267
  • [5] Surgical scene generation and adversarial networks for physics-based iOCT synthesis
    Sommersperger, Michael
    Martin-Gomez, Alejandro
    Mach, Kristina
    Gehlbach, Peter Louis
    Nasseri, M. Ali
    Iordachita, Iulian
    Navab, Nassir
    BIOMEDICAL OPTICS EXPRESS, 2022, 13 (04) : 2414 - 2430
  • [6] Physics-based keyframe selection for human motion summarization
    Athanasios Voulodimos
    Ioannis Rallis
    Nikolaos Doulamis
    Multimedia Tools and Applications, 2020, 79 : 3243 - 3259
  • [7] Physics-based keyframe selection for human motion summarization
    Voulodimos, Athanasios
    Rallis, Ioannis
    Doulamis, Nikolaos
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (5-6) : 3243 - 3259
  • [8] Physics-based Motion Retargeting from Sparse Inputs
    Reda, Daniele
    Won, Jungdam
    Ye, Yuting
    De Panne, Michiel Van
    Winkler, Alexander
    PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2023, 6 (03)
  • [9] Robust Realtime Physics-based Motion Control for Human Grasping
    Zhao, Wenping
    Zhang, Jianjie
    Min, Jianyuan
    Chai, Jinxiang
    ACM TRANSACTIONS ON GRAPHICS, 2013, 32 (06):
  • [10] Generation of equivalent circuits from physics-based device simulation
    Pacelli, A
    Mastrapasqua, M
    Luryi, S
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2000, 19 (11) : 1241 - 1250