Original title: Image demosaicing using Deep Image Prior
Authors: Balušík, Peter
Document type: Papers
Language: eng
Publisher: Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Abstract: The paper focuses on the problem of image demosaicingusing the deep image prior. The deep image prior (DIP)is an uncommon concept that uses a generative neural networkwhich, however, utilizes only the degraded image as the inputfor training. A novel method for image demosaicing is proposed,based on DIP, and it is compared with common demosaicingmethods. In terms of the objective PSNR and SSIM values,the proposed method proved to be comparable with a widelyused Malvar’s demosaicing method. Nevertheless, subjectively,DIP produces demosaiced images comparable with the superiorMenon’s algorithm. Unfortunately, the proposed method turnedout to be computationally immensely challenging
Keywords: color filter array; debayerization; deep image prior; demosaicing
Host item entry: Proceedings II of the 29st Conference STUDENT EEICT 2023: Selected papers, ISBN 978-80-214-6154-3, ISSN 2788-1334

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: http://hdl.handle.net/11012/210671

Permalink: http://www.nusl.cz/ntk/nusl-531777


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Conference materials > Papers