3D reconstruction with depth prior using graph-cut

Hichem Abdellali () and Zoltan Kato ()
Additional contact information
Hichem Abdellali: University of Szeged
Zoltan Kato: University of Szeged

Central European Journal of Operations Research, 2021, vol. 29, issue 2, No 2, 387-402

Abstract: Abstract In this paper, we propose a novel graph-cut based 3D reconstruction method which is able to take into account partially available depth data as a prior. We formulate the energy as a function written as a sum of terms that can be minimized in two different representations: (1) assignment-based, which yields a standard binary energy, in this approach occlusion and uniqueness is handled naturally; as well as (2) a multi-label representation which yields to a non-binary energy where occlusion is only handled by assigning a special label to occluded pixels, while uniqueness is not handled explicitly. Both representations have its advantages and disadvantages, which are analyzed and discussed in detail through various experimental results on the publicly available Middlebury stereo datasets and on real stereo images. Results show, that the use of depth prior information from different sources produces better 3D reconstructions.

Keywords: 3D reconstruction; Graph-cut; Depth prior; MRF modeling (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10100-020-00694-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:cejnor:v:29:y:2021:i:2:d:10.1007_s10100-020-00694-6

Ordering information: This journal article can be ordered from
http://www.springer. ... search/journal/10100

DOI: 10.1007/s10100-020-00694-6

Access Statistics for this article

Central European Journal of Operations Research is currently edited by Ulrike Leopold-Wildburger

More articles in Central European Journal of Operations Research from Springer, Slovak Society for Operations Research, Hungarian Operational Research Society, Czech Society for Operations Research, Österr. Gesellschaft für Operations Research (ÖGOR), Slovenian Society Informatika - Section for Operational Research, Croatian Operational Research Society
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().