A comparative study on super resolution with deep learning
Yükleniyor...
Dosyalar
Tarih
2018
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
IEEE
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Deep learning architectures are applied in the solution of many problems and give very successful results compared to other methods. One of these problems is the Super Resolution problem. In this study, we tried to solve the problem of super resolution by using different deep learning architectures to obtain higher resolution images. The models used in this study are focused on the images scaled up by factors of 2, 3 and 4. As a result of the experimental studies, the model success is increased as the network depth and samples are increased. Instead of a shallow model with more number of parameters, a deep model with lower number of parameters offers more successful results.
Deep learning architectures are applied in the solution of many problems and give very successful results compared to other methods. One of these problems is the Super Resolution problem. In this study, we tried to solve the problem of super resolution by using different deep learning architectures to obtain higher resolution images. The models used in this study are focused on the images scaled up by factors of 2, 3 and 4. As a result of the experimental studies, the model success is increased as the network depth and samples are increased. Instead of a shallow model with more number of parameters, a deep model with lower number of parameters offers more successful results
Deep learning architectures are applied in the solution of many problems and give very successful results compared to other methods. One of these problems is the Super Resolution problem. In this study, we tried to solve the problem of super resolution by using different deep learning architectures to obtain higher resolution images. The models used in this study are focused on the images scaled up by factors of 2, 3 and 4. As a result of the experimental studies, the model success is increased as the network depth and samples are increased. Instead of a shallow model with more number of parameters, a deep model with lower number of parameters offers more successful results
Açıklama
Book Series: Signal Processing and Communications Applications Conference
Anahtar Kelimeler
Deep learning, Super resolution, Bicubic interpolation, Convolutional neural network, Derin öğrenme, Süper çözünürlük, Çift kübik ara değerleme, Katlamalı sinir ağı
Kaynak
26th Signal Processing and Communications Applications Conference (SIU)
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
Sayı
Künye
Temiz, H., Tüfekci, A., & Bilge, H. Ş. (2018). A comparative study on super resolution with deep learning. In 2018 26th Signal Processing and Communications Applications Conference (SIU), İzmir, TURKEY
