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
  • [21] Physics-based modelling of human motion using kalman filter and collision avoidance algorithm
    Perse, M
    Pers, J
    Kristan, M
    Kovacic, S
    ISPA 2005: PROCEEDINGS OF THE 4TH INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS, 2005, : 328 - 333
  • [22] Evaluating the Lidar/HSI Direct Method for Physics-Based Scene Modeling
    Givens, Ryan N.
    Walli, Karl C.
    Eismann, Michael T.
    2014 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2014,
  • [23] Scene layout from ground contact, occlusion, and motion parallax
    Ni, Rui
    Braunstein, Myron L.
    Andersen, George J.
    VISUAL COGNITION, 2007, 15 (01) : 48 - 68
  • [24] Perception of scene layout from optical contact, shadows, and motion
    Ni, R
    Braunstein, ML
    Andersen, GJ
    PERCEPTION, 2004, 33 (11) : 1305 - 1318
  • [25] Learning Models for Constraint-based Motion Parameterization from Interactive Physics-based Simulation
    Fang, Zhou
    Bartels, Georg
    Beetz, Michael
    2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), 2016, : 4005 - 4012
  • [26] Physics-based subsurface visualization of human tissue
    Sharp, Richard
    Adams, Jacob
    Machiraju, Raghu
    Lee, Robert
    Crane, Robert
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2007, 13 (03) : 620 - 629
  • [27] Learning physics-based motion style with nonlinear inverse optimization
    Liu, CK
    Hertzmann, A
    Popovic, Z
    ACM TRANSACTIONS ON GRAPHICS, 2005, 24 (03): : 1071 - 1081
  • [28] Physics-based Motion Capture Imitation with Deep Reinforcement Learning
    Chentanez, Nuttapong
    Muller, Matthias
    Macklin, Miles
    Makoviychuk, Viktor
    Jeschke, Stefan
    ACM SIGGRAPH CONFERENCE ON MOTION, INTERACTION, AND GAMES (MIG 2018), 2018,
  • [29] Robust Physics-based Motion Retargeting with Realistic Body Shapes
    Al Borno, Mazen
    Righetti, Ludovic
    Black, Michael J.
    Delp, Scott L.
    Fiume, Eugene
    Romero, Javier
    COMPUTER GRAPHICS FORUM, 2018, 37 (08) : 81 - 92
  • [30] SHAPE AND NONRIGID MOTION ESTIMATION THROUGH PHYSICS-BASED SYNTHESIS
    METAXAS, D
    TERZOPOULOS, D
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (06) : 580 - 591