Spatial and angular resolution enhancement of light fields using convolutional neural networks

Basit Öğe Kaydı
dc.authorid0000-0002-2679-9733
dc.authorid0000-0003-0779-9620
dc.contributor.authorGül, Muhammed Shahzeb Khan
dc.contributor.authorGüntürk, Bahadır Kürşat
dc.date.accessioned10.07.201910:49:13
dc.date.accessioned2019-07-10T19:50:37Z
dc.date.available10.07.201910:49:13
dc.date.available2019-07-10T19:50:37Z
dc.date.issued2018
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü
dc.descriptionWOS: 000426272000006
dc.descriptionPubMed ID: 29432097
dc.description.abstractLight field imaging extends the traditional photography by capturing both spatial and angular distribution of light, which enables new capabilities, including post-capture refocusing, post-capture aperture control, and depth estimation from a single shot. Micro-lens array (MLA) based light field cameras offer a cost-effective approach to capture light field. A major drawback of MLA based light field cameras is low spatial resolution, which is due to the fact that a single image sensor is shared to capture both spatial and angular information. In this paper, we present a learning based light field enhancement approach. Both spatial and angular resolution of captured light field is enhanced using convolutional neural networks. The proposed method is tested with real light field data captured with a Lytro light field camera, clearly demonstrating spatial and angular resolution improvement.
dc.description.sponsorshipTUBITAK [114E095]en_US
dc.description.sponsorshipThis work was supported by TUBITAK under Grant 114E095.en_US
dc.identifier.citationGül, M. S. K. ve Güntürk, B. (2018). Spatial and angular resolution enhancement of light fields using convolutional neural networks. IEEE Transactions on Image Processing, 27(5), 2146-2159. https://dx.doi.org/10.1109/TIP.2018.2794181
dc.identifier.doi10.1109/TIP.2018.2794181
dc.identifier.endpage2159
dc.identifier.issn1057-7149
dc.identifier.issn1941-0042
dc.identifier.issue5
dc.identifier.scopusqualityQ1
dc.identifier.startpage2146
dc.identifier.urihttps://dx.doi.org/10.1109/TIP.2018.2794181
dc.identifier.urihttps://hdl.handle.net/20.500.12511/2032
dc.identifier.volume27
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherIEEE-Inst Electrical Electronics Engineers Inc
dc.relation.ecinfo:eu-repo/grantAgreement/TUBITAK/SOBAG/114E095
dc.relation.ispartofIEEE Transactions on Image Processingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectLight Field
dc.subjectSuper-Resolution
dc.subjectConvolutional Neural Network
dc.titleSpatial and angular resolution enhancement of light fields using convolutional neural networks
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Güntürk, B..pdf
Boyut:
4.16 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Makale Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu