Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation

Name: Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation
Author: Ateş, Hasan Fehmi, Yildirim, S., Gunturk, B. K.

İsim	Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation
Yazar	Ateş, Hasan Fehmi, Yildirim, S., Gunturk, B. K.
Basım Tarihi:	2023-08
Basım Yeri	- Elsevier
Konu	Blind, Deep network, Iterative, Super-resolution
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	1077-3142
Kayıt Numarası	6a90d27c-ff1b-4661-8f05-a7edebdc4246
Lokasyon	Computer Science
Tarih	2023-08
Notlar	TÜBİTAK
Örnek Metin	Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life images make it difficult to solve this problem using naïve deep learning approaches, where models are often trained on synthetically generated image pairs. Most of the effort so far has been focused on solving the inverse problem under some constraints, such as for a limited space of blur kernels and/or assuming noise-free input images. Yet, there is a gap in the literature to provide a well-generalized deep learning-based solution that performs well on images with unknown and highly complex degradations. In this paper, we propose IKR-Net (Iterative Kernel Reconstruction Network) for blind SISR. In the proposed approach, kernel and noise estimation and high-resolution image reconstruction are carried out iteratively using dedicated deep models. The iterative refinement provides significant improvement in both the reconstructed image and the estimated blur kernel even for noisy inputs. IKR-Net provides a generalized solution that can handle any type of blur and level of noise in the input low-resolution image. IKR-Net achieves state-of-the-art results in blind SISR, especially for noisy images with motion blur.
DOI	10.1016/j.cviu.2023.103718
Cilt	233

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation

Yazar Ateş, Hasan Fehmi, Yildirim, S., Gunturk, B. K.

Basım Tarihi 2023-08

Basım Yeri - Elsevier

Konu Blind, Deep network, Iterative, Super-resolution

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 1077-3142

Kayıt Numarası 6a90d27c-ff1b-4661-8f05-a7edebdc4246

Lokasyon Computer Science

Tarih 2023-08

Notlar TÜBİTAK

Örnek Metin Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life images make it difficult to solve this problem using naïve deep learning approaches, where models are often trained on synthetically generated image pairs. Most of the effort so far has been focused on solving the inverse problem under some constraints, such as for a limited space of blur kernels and/or assuming noise-free input images. Yet, there is a gap in the literature to provide a well-generalized deep learning-based solution that performs well on images with unknown and highly complex degradations. In this paper, we propose IKR-Net (Iterative Kernel Reconstruction Network) for blind SISR. In the proposed approach, kernel and noise estimation and high-resolution image reconstruction are carried out iteratively using dedicated deep models. The iterative refinement provides significant improvement in both the reconstructed image and the estimated blur kernel even for noisy inputs. IKR-Net provides a generalized solution that can handle any type of blur and level of noise in the input low-resolution image. IKR-Net achieves state-of-the-art results in blind SISR, especially for noisy images with motion blur.

DOI 10.1016/j.cviu.2023.103718

Cilt 233