福利在线免费

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 .

The Deep-FIR was featured as a news item on TVM where we have described the preliminary results obtained by this project. A link to the news article and video can be found .

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.

We have presented a short video during the Science in the City event that took place between the 24 and 25 of September 2020.

Dr. Ing. Reuben Farrugia and Dr. Ing. Gianluca Valentino from the Department of Communications and Computer Engineering – University of Malta and members of the Data Science Research Group together with researchers on the Deep-FIR and SAT-FIRE project (Dr. Christian Galea and Dr. David Lloyd respectively), reached out to secondary students from De La Salle College, St. Joseph (Paola) and St. Michael as part of the Career’s day organized at De La Salle College. The students had the opportunity to learn more about data science and how it is used to improve the quality of CCTV videos and Satellite image.

The Deep-FIR project was presented during the Meet the Researcher event during Science in the City which took place in Valletta. This event allows the general public to meet researchers and have a chance to disseminate our ongoing work in a fund, interactive environment.

Reuben Farrugia has presented the Deep-FIR project during the European Network of Forensic Science Institutes (ENFSI) Digital Imaging Working Group (DIWG) organized in Bled, Slovenia. The aim of this working group is to exchange information, develop best practice and standards and exchanged data in the field of forensic science.

We have a position for a post-doc researcher to work on the Deep-FIR research project聽financed by the Fusion R&I Technology Development Progarmme of 2018.聽This post is for a period of 30 months and carries an initial annual remuneration of EUR31,200.聽 The call will close on the 17th of July 2018. A link to the call can be found at the following link:

/__data/assets/pdf_file/0011/356744/FTRSOIII-Deep-FIR-26.06.18.pdf