Publication Details
Poor Man's Virtual Camera: Real-Time Simultaneous Matting and Camera Pose Estimation
Dubská Markéta, Ing., Ph.D. (DCGM FIT BUT)
Zachariáš Michal, Ing., Ph.D. (DCGM FIT BUT)
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT)
augmented reality, cameras, mobile computing, camera pose estimation, real-time systems
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.
@ARTICLE{FITPUB12233, author = "Istv\'{a}n Szentandr\'{a}si and Mark\'{e}ta Dubsk\'{a} and Michal Zachari\'{a}\v{s} and Adam Herout", title = "Poor Man's Virtual Camera: Real-Time Simultaneous Matting and Camera Pose Estimation", pages = "108--119", journal = "IEEE Computer Graphics and Applications", volume = 39, number = 6, year = 2019, ISSN = "0272-1716", doi = "10.1109/MCG.2016.39", language = "english", url = "https://www.fit.vut.cz/research/publication/12233" }