Restore Very Low-Resolution Facial Images
The Deep-FIR project has been featured in February 5th’s edition of The Sunday Times of Malta! The article may also be viewed online here.
Titled ‘The use of AI for image restoration‘, the article provides a high-level overview of super-resolution and the research that was done in the Deep-FIR project at the University of Malta.
The latest research done in the Deep-FIR project has just been published in MDPI Sensors, titled ‘The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks’.
The paper details a novel approach where existing super-resolution models can be modified to utilise supplementary information in the form of degradation prediction in order to further improve performance and to better reflect real-world scenarios where degradation information needs to be estimated.
The paper may be found here. The code accompanying the paper is also available here, with models available for download here.
The talk titled ‘Image Super Resolution using Deep learning’ was given by Prof. John Abela, Principal Investigator of the Deep-FIR project and Associate Professor at the Faculty of ICT, at the first International IEEE Region 8 Robot Championship.
The event, held on Sunday 4th December at the Montekristo Estate, saw a number of robots designed and built by IEEE Student branch members with the aim of promoting Science, Technology, Engineering, and Mathematics (STEM).
The talk provided an overview of super-resolution and the Deep-FIR project, along with examples of applications and super-resolved images. A number of interesting questions were also taken from the audience, including by younger attendees.
We at Deep-FIR thank you for attending the talk, and look forward to meeting you at any other future events! These will be advertised on this website, on the project’s Facebook page, and on the project’s LinkedIn page, so make sure to follow any one (or all!) of these to get notified of any such events and other news related to the project.
An article posted on LinkedIn last week highlighted a number of issues in the field of image super-resolution; now, the potential solutions to these problems are discussed.
The article contains some additional information to that already published as part of the Deep-FIR project, exclusive to LinkedIn followers.
The article may be viewed here. Remember to ‘Follow’ the Deep-FIR page on LinkedIn to make sure that you are kept up-to-date with all the latest news and updates related to the project!
An article serving as a continuation of last week’s article has been published on LinkedIn, where a more in-depth discussion on the issues in super-resolution is provided.
The article contains some additional information to that already published as part of the Deep-FIR project, exclusive to LinkedIn followers.
The article may be viewed here. Remember to ‘Follow’ the Deep-FIR page on LinkedIn to make sure that you are kept up-to-date with all the latest news and updates related to the project!
An article serving as an introduction to super-resolution and its uses in the real world has been published on LinkedIn.
The article contains some additional information to that already published as part of the Deep-FIR project, exclusive to LinkedIn followers.
The article may be viewed here. Remember to ‘Follow’ the Deep-FIR page on LinkedIn to make sure that you are kept up-to-date with all the latest news and updates related to the project!
Dr Ing. Christian Galea, one of the researchers in the Deep-FIR project, was invited to be part of a panel on the programme ‘Ġimgħa b’Ġimgħa‘ to discuss the work being done at the Faculty of ICT with regards to security and law enforcement.
Together with the other panelists, Dr Christian Colombo and Dr Joseph G Vella, a number of issues and research projects were discussed. Dr Ing. Galea talked about the work being done on super-resolution in the Deep-FIR project, among other research and applications related to biometrics and forensics.
The programme, aired on NET TV (in Maltese), may be viewed in full here.
We thank the production team of ‘Ġimgħa b’Ġimgħa‘ and the crew at NET TV for inviting Dr Ing. Galea and showcasing the work being done at the Faculty of ICT.
The articles recently published on the Towards Data Science platform (as mentioned in a previous post announcing the publication the first article and the publication of the second article) have recently been featured on the University of Malta’s news portal, Newspoint. The article may be viewed here.
Following the publication of the first article on the highly popular Towards Data Science website, the second article has now also been published.
The article, titled ‘Image Super-Resolution: An Overview of the Current State of Research‘, deals with a review of popular techniques and remaining challenges in the field of image super-resolution.
We again hope that you enjoy reading the article and find it informative. Make sure to follow this website or any of our social media channels (Facebook and LinkedIn) to remain updated with the latest news related to the Deep-FIR project. You may also follow the author (Dr Ing. Christian Galea) on Medium to ensure that you’re updated whenever a new article is published.
Towards Data Science is a publication dedicated to data science that is available on Medium. It has become hugely popular and is one of the most-visited websites in its category, having around 18 million visits per month.
An article regarding an introduction to super-resolution and issues in the field, written as part of the Deep-FIR project, has just been published on Towards Data Science and may be viewed here.
We hope you enjoy reading the article and find it informative. Another article is planned for publication in the coming days and weeks, so stay tuned to the news section on this website or follow the author (Dr Ing. Christian Galea) on Medium to ensure that you’re updated when a new article is published.