Publication detail

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

SZENTANDRÁSI, I. JURÁNKOVÁ, M. ZACHARIÁŠ, M. HEROUT, A.

Original Title

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

English Title

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

Type

journal article in Web of Science

Language

en

Original Abstract

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.

English abstract

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.

Keywords

augmented reality, cameras, mobile computing, camera pose estimation, real-time systems

Released

01.12.2019

Publisher

NEUVEDEN

Location

NEUVEDEN

ISBN

0272-1716

Periodical

IEEE COMPUTER GRAPHICS AND APPLICATIONS

Year of study

39

Number

6

State

US

Pages from

108

Pages to

119

Pages count

12

URL

Documents

BibTex


@article{BUT163433,
  author="István {Szentandrási} and Markéta {Juránková} and Michal {Zachariáš} and Adam {Herout}",
  title="Poor Man's Virtual Camera: Real-Time Simultaneous Matting and Camera Pose Estimation",
  annote="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.",
  address="NEUVEDEN",
  chapter="163433",
  doi="10.1109/MCG.2016.39",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="6",
  volume="39",
  year="2019",
  month="december",
  pages="108--119",
  publisher="NEUVEDEN",
  type="journal article in Web of Science"
}