Publication detail

Automated outdoor depth-map generation and alignment

ČADÍK, M. SÝKORA, D. LEE, S.

Original Title

Automated outdoor depth-map generation and alignment

Type

journal article in Web of Science

Language

English

Original Abstract

Image enhancement tasks can highly benefit from depth information, but the direct estimation of outdoor depth maps is difficult due to vast object distances. This paper presents a fully automatic framework for model-based generation of outdoor depth maps and its applications to image enhancements. We leverage 3D terrain models and camera pose estimation techniques to render approximate depth maps without resorting to manual alignment. Potential local misalignments, resulting from insufficient model details and rough registrations, are eliminated with our novel free-form warping. We first align synthetic depth edges with photo edges using the as-rigid-as-possible image registration and further refine the shape of the edges using the tight trimap-based alpha matting. The resulting synthetic depth maps are accurate, calibrated in the absolute distance. We demonstrate their benefit in image enhancement techniques including reblurring, depth-of-field simulation, haze removal, and guided texture synthesis.

Keywords

Image enhancement Synthetic depth 3D terrain Free-form warping Image registration Synthetic camera

Authors

ČADÍK, M.; SÝKORA, D.; LEE, S.

Released

30. 5. 2018

ISBN

0097-8493

Periodical

COMPUTERS & GRAPHICS-UK

Year of study

74

Number

3

State

United Kingdom of Great Britain and Northern Ireland

Pages from

109

Pages to

118

Pages count

10

URL

http://cphoto.fit.vutbr.cz/depth/

BibTex

@article{BUT155059,
  author="ČADÍK, M. and SÝKORA, D. and LEE, S.",
  title="Automated outdoor depth-map generation and alignment",
  journal="COMPUTERS & GRAPHICS-UK",
  year="2018",
  volume="74",
  number="3",
  pages="109--118",
  doi="10.1016/j.cag.2018.05.001",
  issn="0097-8493",
  url="http://cphoto.fit.vutbr.cz/depth/"
}