Iterative kernel reconstruction for deep learning-based blind image super-resolution

Basit Öğe Kaydı
dc.authorid0000-0002-2752-1223
dc.authorid0000-0002-6842-1528
dc.authorid0000-0003-0779-9620
dc.contributor.authorYıldırım, Süleyman
dc.contributor.authorAteş, Hasan Fehmi
dc.contributor.authorGüntürk, Bahadır Kürşat
dc.date.accessioned2023-10-25T06:31:47Z
dc.date.available2023-10-25T06:31:47Z
dc.date.issued2022
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü
dc.description.abstractDeep learning based methods have received a great deal of interest in recent years to solve the single image superresolution (SISR) problem and their performance is proven to be superior when compared to classical SR techniques. Yet, most of these methods fail to generalize well on real life image datasets because they are trained on synthetic datasets with a small range of blur kernels. This makes data-driven approaches inherently weak when it comes to real images. Therefore, applying image super-resolution independently of the blur kernel is still a challenging task. In this paper we propose IKR-Net, Iterative Kernel Reconstruction network, for blind SISR. In the proposed approach, kernel estimation and high resolution image reconstruction are carried out iteratively using deep models. The iterative refinement provides significant improvement in both the reconstructed image and the estimated blur kernel. IKR-Net achieves state-of-the-art results in blind SISR, especially for images with motion blur.
dc.description.sponsorshipThe Institute of Electrical and Electronics Engineers Signal Processing Societyen_US
dc.identifier.citationYıldırım, S., Ateş, H. F. ve Güntürk, B. K. (2022). Iterative kernel reconstruction for deep learning-based blind image super-resolution. IEEE International Conference on Image Processing (ICIP) içinde (3251-3255. ss.). Bordeaux, France, 16-19 October, 2022. https://doi.org/10.1109/ICIP46576.2022.9897266
dc.identifier.doi10.1109/ICIP46576.2022.9897266
dc.identifier.endpage3255
dc.identifier.isbn9781665496209
dc.identifier.issn1522-4880
dc.identifier.scopus2-s2.0-85146576293
dc.identifier.scopusqualityN/A
dc.identifier.startpage3251
dc.identifier.urihttps://doi.org/10.1109/ICIP46576.2022.9897266
dc.identifier.urihttps://hdl.handle.net/20.500.12511/11634
dc.identifier.wos001058109503069en_US
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorYıldırım, Süleyman
dc.institutionauthorAteş, Hasan Fehmi
dc.institutionauthorGüntürk, Bahadır Kürşat
dc.language.isoen
dc.publisherIEEE Computer Society
dc.relation.ispartofIEEE International Conference on Image Processing (ICIP)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.relation.tubitakinfo:eu-repo/grantAgreement/TUBITAK/SOBAG/119E566
dc.rightsinfo:eu-repo/semantics/embargoedAccess
dc.subjectSuper-Resolution
dc.subjectKernel Estimation
dc.subjectBlind
dc.subjectIterative
dc.subjectDeep Learning
dc.titleIterative kernel reconstruction for deep learning-based blind image super-resolution
dc.typeConference Object

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Yildirim-Suleyman-2022.pdf
Boyut:
4.75 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bildiri Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu