External Pressures Bring Changes to Higher Education
21 December 2016
Coffeeshops continue to conquer
21 December 2016
External Pressures Bring Changes to Higher Education
21 December 2016
Top 5 Books to Keep on Your Bookshelf For as Long as You Live
21 December 2016
Facing Your Fears of Returning To School as an Adult
21 December 2016
Primary School Encourages Students to Wear Slippers in Class
21 December 2016

Important Announcement | Kickoff of the "College Geniuses" competition qualifiers for the 2026-2027 academic year 🏆

📢 Important Announcement | Launch of the "College Geniuses" Competition Qualifiers for the 2026-2027 Academic Year 🏆

Under the patronage of:
Prof. Dr. Taysir Hassan Abdel Hamid
Dean of the Faculty of Computers and Information

Prof. Dr. Khaled Fathy Hussein
Vice Dean for Education and Student Affairs

The Cultural Committee, under the Student Welfare Department at the Faculty of Computers and Information, announces the commencement of the qualifiers for the "College Geniuses" competition for the 2026-2027 academic year, open to all students of the Faculty.

This competition is part of the Faculty’s commitment to fostering cultural and intellectual awareness among students, encouraging positive competition, and showcasing their talents and capabilities across various fields of knowledge and culture.

✨ We wish all our students continued success and the best possible results!

Student Welfare Department – ​​Faculty of Computers and Information

#Faculty_of_Computers_and_Information
#Student_Welfare
#Cultural_Committee
#College_Geniuses

 

1

🏆 Congratulations on an outstanding victory in the university-wide table tennis championship! 🏆

🏆 Congratulations on an Outstanding Achievement in the University-Wide Table Tennis Championship 🏆

Under the patronage of:

Prof. Dr. Tayseer Hassan Abdel Hamid
Dean of the Faculty of Computers and Information

And Prof. Dr. Khaled Fathy Hussein
Vice Dean for Education and Student Affairs

The Faculty of Computers and Information, along with the Student Welfare Department, extends its sincere congratulations to student Mohamed Haitham Ibrahim (second-year student) for securing third place in the university-wide table tennis championship, organized by the General Administration of Student Welfare at Assiut University for the 2026-2027 academic year.

This achievement serves as a testament to the student’s excellence and athletic dedication. We wish him continued success and many more commendable accomplishments—reflecting the ability of our faculty’s students to excel and innovate across various student and athletic activities.

Heartiest congratulations, with best wishes for further success and future championship victories!

1

Learning to remove occlusions in light field images using multiscale receptive fields and feature pyramid networks

Research Abstract

Removal of occlusions in light-field (LF) images is strongly influenced by the receptive field of the neural network. Existing methods often suffer from limited receptive fields, restricting their ability to capture long-range dependencies and recover occluded regions effectively. To overcome this, we propose LF-PyrNet, a novel end-to-end deep learning model that enhances occlusion removal through multi-scale receptive field learning and hierarchical feature pyramid-based refinement. Our model consists of three key components. First, the feature extractor expands the receptive field by integrating Residual Atrous Spatial Pyramid Pooling (ResASPP) and a modified receptive field block (RFB). These components allow the model to capture broader context and multi-scale spatial dependencies. Next, the core occlusion reconstruction network consists of three cascaded Residual Dense Blocks (RDBs). Each block contains four densely connected layers. A Feature Pyramid Network (FPN) then performs multi-scale feature fusion and refines the representations effectively. Finally, the refinement module, which incorporates both separable and standard convolutions, enhances detailed structural consistency and improves texture restoration in occluded regions. Experimental results show that expanding the receptive field significantly enhances the occlusion removal performance, making LF-PyrNet a reliable solution for reconstructing occluded regions in LF images.

Research Authors
Mostafa Farouk Senussi, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, Mohamed Mahmoud, Hyun-Soo Kang
Research Date
Research Department
Information Technology Department
Research File
s41598-025-20786-0.pdf (992.76 KB)
Research Image
Overall Architecture of LF-PyrNet for Occlusion Removal in Light Field Images, Consisting of Feature Extraction, Reconstruction, and Refinement.
Research Journal
Scientific Reports
Research Member
Mostafa Farouk
Mahmoud Salah Eldin Mohammed
Mohamed Hamdy Hamdan Mahmoud
Research Pages
36978
Research Publisher
Nature Publishing Group UK
Research Vol
15
Research Website
https://doi.org/10.1038/s41598-025-20786-0
Research Year
2025
Subscribe to