MoSculp: Interactive Visualization of Shape and Time

被引:21
作者
Zhang, Xiuming [1 ]
Dekel, Tali [2 ]
Xue, Tianfan [2 ]
Owens, Andrew [3 ]
He, Qiurui [1 ]
Wu, Jiajun [1 ]
Mueller, Stefanie [1 ]
Freeman, William T. [1 ,2 ]
机构
[1] MIT, CSAIL, Cambridge, MA 02139 USA
[2] Google Res, Mountain View, CA USA
[3] Univ Calif Berkeley, Berkeley, CA USA
来源
UIST 2018: PROCEEDINGS OF THE 31ST ANNUAL ACM SYMPOSIUM ON USER INTERFACE SOFTWARE AND TECHNOLOGY | 2018年
关键词
Motion estimation and visualization; image-based rendering;
D O I
10.1145/3242587.3242592
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We present a system that visualizes complex human motion via 3D motion sculptures-a representation that conveys the 3D structure swept by a human body as it moves through space. Our system computes a motion sculpture from an input video, and then embeds it back into the scene in a 3D-aware fashion. The user may also explore the sculpture directly in 3D or physically print it. Our interactive interface allows users to customize the sculpture design, for example, by selecting materials and lighting conditions. To provide this end-to-end workflow, we introduce an algorithm that estimates a human's 3D geometry over time from a set of 2D images, and develop a 3D-aware image-based rendering approach that inserts the sculpture back into the original video. By automating the process, our system takes motion sculpture creation out of the realm of professional artists, and makes it applicable to a wide range of existing video material. By conveying 3D information to users, motion sculptures reveal space-time motion information that is difficult to perceive with the naked eye, and allow viewers to interpret how different parts of the object interact over time. We validate the effectiveness of motion sculptures with user studies, finding that our visualizations are more informative about motion than existing stroboscopic and space-time visualization methods.
引用
收藏
页码:275 / 285
页数:11
相关论文
共 49 条
  • [11] Brown M., 2007, INT J COMPUTER VISIO
  • [12] Burg Kevin, 2015, SCH AM BALLET
  • [13] Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
    Cao, Zhe
    Simon, Tomas
    Wei, Shih-En
    Sheikh, Yaser
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1302 - 1310
  • [14] Chen Qifeng, 2013, IEEE T PATTERN ANAL
  • [15] Chi Pei-Yu, 2016, ACM S US INT SOFTW T
  • [16] 3D Human Pose Estimation=2D Pose Estimation plus Matching
    Chen, Ching-Hang
    Ramanan, Deva
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5759 - 5767
  • [17] Cutting J. E., 2002, PERCEPTION
  • [18] Freeman William T., 2003, IEEE C COMP VIS PATT
  • [19] Geyer Eyal, 2014, KICK MOTION SCULPTUR
  • [20] GREMMLER T., 2016, Kung Fu Motion Visualization