dc.contributor.author | Yıldırım, Süleyman | |
dc.contributor.author | Ateş, Hasan Fehmi | |
dc.contributor.author | Güntürk, Bahadır Kürşat | |
dc.date.accessioned | 2023-10-25T06:31:47Z | |
dc.date.available | 2023-10-25T06:31:47Z | |
dc.date.issued | 2022 | en_US |
dc.identifier.citation | Yıldırım, 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 | en_US |
dc.identifier.isbn | 9781665496209 | |
dc.identifier.issn | 1522-4880 | |
dc.identifier.uri | https://doi.org/10.1109/ICIP46576.2022.9897266 | |
dc.identifier.uri | https://hdl.handle.net/20.500.12511/11634 | |
dc.description.abstract | Deep 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. | en_US |
dc.description.sponsorship | The Institute of Electrical and Electronics Engineers Signal Processing Society | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE Computer Society | en_US |
dc.rights | info:eu-repo/semantics/embargoedAccess | en_US |
dc.subject | Super-Resolution | en_US |
dc.subject | Kernel Estimation | en_US |
dc.subject | Blind | en_US |
dc.subject | Iterative | en_US |
dc.subject | Deep Learning | en_US |
dc.title | Iterative kernel reconstruction for deep learning-based blind image super-resolution | en_US |
dc.type | conferenceObject | en_US |
dc.relation.ispartof | IEEE International Conference on Image Processing (ICIP) | en_US |
dc.department | İstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü | en_US |
dc.department | İstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü | en_US |
dc.authorid | 0000-0002-2752-1223 | en_US |
dc.authorid | 0000-0002-6842-1528 | en_US |
dc.authorid | 0000-0003-0779-9620 | en_US |
dc.identifier.startpage | 3251 | en_US |
dc.identifier.endpage | 3255 | en_US |
dc.relation.tubitak | info:eu-repo/grantAgreement/TUBITAK/SOBAG/119E566 | |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.identifier.doi | 10.1109/ICIP46576.2022.9897266 | en_US |
dc.institutionauthor | Yıldırım, Süleyman | |
dc.institutionauthor | Ateş, Hasan Fehmi | |
dc.institutionauthor | Güntürk, Bahadır Kürşat | |
dc.identifier.wos | 001058109503069 | en_US |
dc.identifier.scopus | 2-s2.0-85146576293 | en_US |