Poor Man's Virtual Camera: Real-Time Simultaneous Matting and Camera Pose Estimation

被引:0
|
作者
Szentandrasi, Istvan [1 ]
Dubska, Marketa [1 ]
Zacharias, Michal [1 ]
Herout, Adam [1 ]
机构
[1] Brno Univ Technol, Brno, Czech Republic
关键词
LOCALIZATION;
D O I
10.1109/MCG.2016.39
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Today's film and advertisement production heavily uses computer graphics combined with living actors by chroma keying. The matchmoving process typically takes a considerable manual effort. Semiautomatic matchmoving tools exist as well, but they still work offline and require manual check-up and correction. In this paper, we propose an instant matchmoving solution for green screen. It uses a recent technique of planar uniform marker fields. Our technique can be used in indie and professional filmmaking as a cheap and ultramobile virtual camera, and for shot prototyping and storyboard creation. The matchmoving technique based on marker fields of shades of green is very computationally efficient: we developed and present in this paper a mobile application running at 33 FPS. Our technique is thus available to anyone with a smartphone at low cost and with an easy setup, opening space for new levels of filmmakers' creative expression.
引用
收藏
页码:108 / 119
页数:12
相关论文
共 50 条
  • [1] Real-time camera pose estimation for sports fields
    Leonardo Citraro
    Pablo Márquez-Neila
    Stefano Savarè
    Vivek Jayaram
    Charles Dubout
    Félix Renaut
    Andrés Hasfura
    Horesh Ben Shitrit
    Pascal Fua
    Machine Vision and Applications, 2020, 31
  • [2] Real-time camera pose estimation for sports fields
    Citraro, Leonardo
    Marquez-Neila, Pablo
    Savare, Stefano
    Jayaram, Vivek
    Dubout, Charles
    Renaut, Felix
    Hasfura, Andres
    Ben Shitrit, Horesh
    Fua, Pascal
    MACHINE VISION AND APPLICATIONS, 2020, 31 (03)
  • [3] Real-time camera pose and focal length estimation
    Jain, Sumit
    Neumann, Ulrich
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 551 - +
  • [4] Real-time camera pose in a room
    Chandraker, MK
    Stock, C
    Pinz, A
    COMPUTER VISION SYSTEMS, PROCEEDINGS, 2003, 2626 : 98 - 110
  • [5] Real-time camera pose estimation via line tracking
    Liu, Yanli
    Chen, Xianghui
    Gu, Tianlun
    Zhang, Yanci
    Xing, Guanyu
    VISUAL COMPUTER, 2018, 34 (6-8): : 899 - 909
  • [6] Real-time camera pose estimation via line tracking
    Yanli Liu
    Xianghui Chen
    Tianlun Gu
    Yanci Zhang
    Guanyu Xing
    The Visual Computer, 2018, 34 : 899 - 909
  • [7] Multi-camera system for real-time pose estimation
    Savakis, Andreas
    Erhard, Matthew
    Schimmel, James
    Hnatow, Justin
    INTELLIGENT COMPUTING: THEORY AND APPLICATIONS V, 2007, 6560
  • [8] Real-Time Simultaneous Pose and Shape Estimation for Articulated Objects Using a Single Depth Camera
    Ye, Mao
    Shen, Yang
    Du, Chao
    Pan, Zhigeng
    Yang, Ruigang
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (08) : 1517 - 1532
  • [9] Real-time Simultaneous Pose and Shape Estimation for Articulated Objects Using a Single Depth Camera
    Ye, Mao
    Yang, Ruigang
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 2353 - 2360
  • [10] Real-Time Camera Pose Estimation Based on Multiple Planar Markers
    Yu, Rui
    Yang, Tao
    Zheng, Jiangbin
    Zhang, Xingong
    PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS (ICIG 2009), 2009, : 640 - 645