Skip to main content

Recreational Games League

 

 

 

 

 

Training courses offered by the Information Technology Institute, specializing in a distinguished technological field, for graduates of Egyptian universities from 2016 to 2025, at the institute's headquarters in Assiut Governorate.

https://www.facebook.com/share/p/16Q5x1TjuB/

Training Courses Offered in Assiut Governorate The Information Technology Institute announces the opening of registration for intensive training grants in a distinguished technological specialization for Egyptian university graduates from 2016 to 2025 at the institute's headquarters in Assiut Governorate. The courses are as follows: Full Stack Web Development Using MEARN For more information about the specialization, please visit the following link:

https://drive.google.com/.../1FCUYqXP5ub7z8iWXgpv.../view...

2D Graphics Design For more information about the specialization, please visit the following link:

https://drive.google.com/.../13qqxtSv0tEqwf.../view...

- Required documents and registration steps are explained in the registration link. - The training courses will be conducted using a blended learning system. - Registration begins on Saturday, November 1, 2025, and continues until [date missing]. Thursday, November 13, 2025 - Registration is through the following link on the official website of the Information Technology Institute:

https://internal.iti.gov.eg/home

Spectral Normalized U-Net for Light Field Occlusion Removal

Research Abstract

Occlusion artifacts significantly hinder light field (LF) image reconstruction, especially in complex scenes. We propose a spectral normalized U-Net for LF occlusion removal, which begins by stacking LF views and extracting view-dependent features using a local feature encoder. To capture spatial complexity, ResASPP enable multi-scale context aggregation, while channel attention enhances occlusion-related features. Spectral normalization is applied to all convolutional layers to improve training stability and generalization. The encoder-decoder structure with skip connections preserves fine details. Experimental results show our method restores occluded regions more accurately than baselines.

Research Authors
Mostafa Farouk Senussi, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, Mohamed Mahmoud, Hyun-Soo Kang
Research Date
Research Department
Research Image
Overview of the Proposed Spectral Normalized U-Net for Occlusion Removal in LF Images
Research Journal
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
Research Pages
294-297
Research Publisher
Korea Information and Communications Society
Research Vol
16
Research Website
https://www.dbpia.co.kr/pdf/pdfView.do?nodeId=NODE12293106
Research Year
2025
Subscribe to