福利在线免费

News and Events

Posted on

Deep-FIR presented at Science in the City 2022

As announced in a previous post, Deep-FIR was presented at the recently held Science in the City 2022.

Prof. John Abela, Principal Investigator of the Deep-FIR project, gave an overview of super-resolution, its applications, and a number of examples of existing algorithms on the stand of the Faculty of 福利在线免费 and Communication Technology (ICT).

Attendees were invited to ask questions, and a number of interesting points were discussed.

We at Deep-FIR thank you for attending the presentation, and look forward to meeting you at any other future events! These will be advertised on this website, on the project’s , and on the project’s , 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.

Posted on

Deep-FIR at Science in the City 2022

, a highly popular annual festival, will be taking place tomorrow, Friday 30th September, and on Saturday 1st October, at Valletta (Malta).

As always, a variety of interesting projects, organisations, and so on will be exhibited – including the Deep-FIR project. A talk will be given tomorrow (Friday 30th September) at 21:30 on the Faculty of ICT’s stand, where other presentations will also be given between 18:00 and 23:00.

Any visitors will have the opportunity to ask questions and have a chat with the team. We look forward to seeing you there!

Posted on

Deep-FIR now on LinkedIn!

Deep-FIR now showcased on LinkedIn!

Apart from being featured on this website and on Facebook, you may now also get the latest updates related to the Deep-FIR project on another social media platform – meet the new !

Make sure to ‘follow‘ the page to receive the latest news on upcoming events, news, and exclusive articles related to super-resolution and the research being done in the Deep-FIR project.

Posted on

Deep-FIR presented at Actable AI event

Dr Ing. Christian Galea giving an overview of the Deep-FIR project at the Actable AI meet up.

Dr Ing. Christian Galea, post-doctoral researcher at the University of Malta and a member of the Deep-FIR project team, was recently invited as a guest speaker at a hosted by . A number of stakeholders and practitioners in the field of data science and iGaming attended the event which took place at .

A number of topics were presented and discussed during the talk, entitled ‘An Overview of Data Science and Data Analytics, and their Relation to Computer Vision’, including the research being done in the Deep-FIR project. A Q&A panel was also held where attendees were able to ask any questions related to the presented information.

The response to the topics presented, including the Deep-FIR project, was very positive and a number of interesting questions and observations were discussed.

We at Deep-FIR look forward to presenting the project in future events!

Posted on

Participation at the Faculty of ICT Projects Exhibition

Last week, the Deep-FIR team took part in the annual ICT Projects Exhibition, hosted by the Faculty of ICT. Throughout the three-day event, the main areas of our work were highlighted in an and through a (overview at 1:20:52 and discussion at 1:41:30). For the latter, we discussed the various facets of super-resolution, and emphasized the importance of such work when considering real-world imaging devices, such as CCTV systems and smartphones. In the article, we go into a little more detail and give an overview of our main areas of focus, namely video/multi-frame super-resolution, blind super-resolution and metadata-guided super-resolution.

Posted on

Published work on IEEE Signal Processing Letters

The Deep-FIR team has recently published a paper on . In we presented a new mechanism that integrates additional information (metadata) describing the degradation process (such as the blur kernel applied, compression level, etc.) to guide the neural network to super-resolve low-resolution images with higher fidelity to the original source. This proposed meta-attention module can be integrated within existing super-resolution techniques to exploit the information available in relevant degradation parameters to improve its performance. This approach was found to improve the performance by 0.3 dB in terms of PSNR. The coding framework used for this paper is available at .

Posted on

Press Release: Restoration of CCTV quality face images

Our team has adopted an advanced artificial intelligence (AI) technique based on deep-learning to restore very low-resolution and compressed images. The developed algorithm has shown that it is capable of restoring degradations that are typically present in CCTV footage. The figure shows a number of low-quality facial images on the left and the restored images on the right. By comparing the restored face to the actual high-resolution face, one can see that the proposed method is able to significantly improve the quality of the face while preserving the identity of the person of interest. More information about the press relase can be found here.