IEEE Mediterranean Eletrotechnical Conference 2020

IEEE MELECON 2020

You should be logged in to see the presentation

Conference Track

Session 2.3 - Artificial Intelligence and Big Data Analytics

An Approach for Objective Quality Assessment of Image Inpainting Results

  Dylan Seychell

  • 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 inpainting 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.

  • PRESENTER

Dylan Seychell
  University of Malta, Malta

  • QUESTIONS & ANSWERS

There are still no questions. Be the first to post one!

  • SEND YOUR QUESTION