Please use this identifier to cite or link to this item:
Title: An approach for objective quality assessment of image inpainting results
Authors: Seychell, Dylan
Debono, Carl James
Keywords: Inpainting
Data sets
Computer vision
Machine learning
Issue Date: 2020
Publisher: IEEE
Citation: Seychell, D., & Debono, C. J. (2020). An approach for objective quality assessment of image inpainting results. 20th Mediterranean Electrotechnical Conference (MELECON), Palermo. 226-231.
Abstract: Image Inpainting techniques are generally challenging to evaluate objectively due to the lack of comparative data, as a reference image of the new scene, does not exist.. This paper presents an approach that uses our newly released dataset specifically designed to allow objective evaluation of inpainting techniques. In this work we demonstrate how traditional in-painting techniques can be objectively evaluated and compared together with modern deep learning and adversarial approaches. We further demonstrate how an unsupervised technique compares better than deep learning approaches.
Appears in Collections:Scholarly Works - FacICTAI

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.36 MBAdobe PDFView/Open Request a copy

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.