Faculty of Information Technology, BUT

Publication Details

Automated outdoor depth-map generation and alignment

ČADÍK Martin, SÝKORA Daniel and LEE Sungkil. Automated outdoor depth-map generation and alignment. Computers and Graphics, vol. 74, no. 3, pp. 109-118. ISSN 0097-8493. Available from: http://cphoto.fit.vutbr.cz/depth/
Czech title
Automatická syntéza a registrace hloubkové mapy pro fotografie přírody
Type
journal article
Language
english
Authors
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT)
Sýkora Daniel (ČVUT)
Lee Sungkil, Ph.D. (SKKU)
URL
Keywords
Image enhancement
Synthetic depth
3D terrain
Free-form warping
Image registration
Synthetic camera
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.
Annotation
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.

Our method allows to register synthetic depth maps with an outdoor photographs for subsequent editing, which has not been possible until now. This unique feature may be applied in virtual and augmented reality systems as well as in image editing software.

This work has been published as an impacted journal paper (Computers & Graphics 2018), and it is available online: https://www.sciencedirect.com/science/article/pii/S0097849318300608
Supplementary materials and a video summarizing our paper are available on the project webpage: http://cphoto.fit.vutbr.cz/depth/
Published
2018
Pages
109-118
Journal
Computers and Graphics, vol. 74, no. 3, ISSN 0097-8493
Publisher
Elsevier Science
DOI
BibTeX
@ARTICLE{FITPUB11745,
   author = "Martin \v{C}ad\'{i}k and Daniel S\'{y}kora and Sungkil Lee",
   title = "Automated outdoor depth-map generation and alignment",
   pages = "109--118",
   journal = "Computers and Graphics",
   volume = 74,
   number = 3,
   year = 2018,
   ISSN = "0097-8493",
   doi = "10.1016/j.cag.2018.05.001",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11745"
}
Back to top