Zurück zur Übersicht

Fast Multi-Level Foreground Estimation

full text: PDF
author/s: Thomas Germer, Tobias Uelwer, Stefan Conrad, Stefan Harmeling
type:Inproceedings
booktitle:2020 25th International Conference on Pattern Recognition (ICPR)
month:October
year:2020
language:English
copyright:The Institute of Electrical and Electronics Engineers, Incorporated (IEEE)
note:to be published, the linked PDF is a preprint
Abstract

Alpha matting aims to estimate the translucency of an object in a given image. The resulting alpha matte describes pixel-wise to what amount foreground and background colors contribute to the color of the composite image. While most methods in literature focus on estimating the alpha matte, the process of estimating the foreground colors given the input image and its alpha matte is often neglected, although foreground estimation is an essential part of many image editing workflows. In this work, we propose a novel method for foreground estimation given the alpha matte. We demonstrate that our fast multi-level approach yields results that are comparable with the state-of-the-art while outperforming those methods in computational runtime and memory usage.

Heinrich Heine Universität

Datenbanken und Informationssysteme

Lehrstuhlinhaber

Prof. Dr. Stefan Conrad


Universitätsstr. 1
40225 Düsseldorf
Gebäude: 25.12
Etage/Raum: 02.24
Tel.: +49 211 81-14088

Sekretariat

Sabine Freese


Sprechzeiten:
Mo-Fr: 10:00-11:30 Uhr
Mo-Do: 13:00-14:30 Uhr


Universitätsstr. 1
40225 Düsseldorf
Gebäude: 25.12
Etage/Raum: 02.22
Tel.: +49 211 81-11312
Fax: +49 211 81-13463
Verantwortlich für den Inhalt:  E-Mail senden Datenbanken & Informationssysteme