Dépôt Institutionnel de l'Université BBA

Application of generative adversarial networks for image super Resolution

Afficher la notice abrégée

dc.contributor.author BAHRI Chaima, DERROU Mehdi
dc.date.accessioned 2024-09-25T09:23:48Z
dc.date.available 2024-09-25T09:23:48Z
dc.date.issued 2024-06
dc.identifier.uri https://dspace.univ-bba.dz:443/xmlui/handle/123456789/5486
dc.description.abstract In image super-resolution applications, generative adversarial networks (GANs) are often employed to convert low-resolution images into high-resolution ones, thus improving image quality. These networks are made up of a discriminator network that assesses the validity of the generated samples and a generator network that generates new samples based on the data. Image quality has been significantly improved using GANs, especially in situations where data samples are scarce. In this thesis, we are implemented and tested a several models of image super resolution based on GANs such as: SRGAN, ESRGAN and Real ESRGAN. We compared the obtained results of the deep learning methods with traditional methods like Bicubic interpolation using the PSNR and the SSIM metrics. en_US
dc.language.iso en en_US
dc.publisher faculté des sciences et de la technologie* univ bba en_US
dc.relation.ispartofseries ;EL/M/2024/16
dc.subject Super-resolution, GAN, SRGAN, ESRGAN, Real-ESRGAN en_US
dc.title Application of generative adversarial networks for image super Resolution en_US
dc.type Thesis en_US


Fichier(s) constituant ce document

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée

Chercher dans le dépôt


Recherche avancée

Parcourir

Mon compte