dc.contributor.author | Qian, Qinchun | |
dc.contributor.author | Güntürk, Bahadır Kürşat | |
dc.date.accessioned | 10.07.201910:49:13 | |
dc.date.accessioned | 2019-07-10T19:37:24Z | |
dc.date.available | 10.07.201910:49:14 | |
dc.date.available | 2019-07-10T19:37:24Z | |
dc.date.issued | 2014 | en_US |
dc.identifier.citation | Qian, Q. ve Güntürk, B. K. (2014). Super-resolution restoration of motion blurred images. Conference on Digital Photography X, San Francisco, CA, 03-05 Şubat 2014. https://dx.doi.org/10.1117/12.2038844 | en_US |
dc.identifier.isbn | 9780819499400 | |
dc.identifier.issn | 0277-786X | |
dc.identifier.issn | 1996-756X | |
dc.identifier.uri | https://hdl.handle.net/20.500.12511/1395 | |
dc.identifier.uri | https://dx.doi.org/10.1117/12.2038844 | |
dc.description.abstract | In this paper, we investigate super-resolution image restoration from multiple images, which are possibly degraded with large motion blur. The blur kernel for each input image is separately estimated. This is unlike many existing super-resolution algorithms, which assume identical blur kernel for all input images. We also do not make any restrictions on the motion fields among images; that is, we estimate dense motion field without simplifications such as parametric motion. We present a two-step algorithm: In the first step, each input image is deblurred using the estimated blur kernel. In the second step, super-resolution restoration is applied to the deblurred images. Because the estimated blur kernels may not be accurate, we propose a weighted cost function for the super-resolution restoration step, where a weight associated with an input image reflects the reliability of the corresponding kernel estimate and the deblurred image. We provide experimental results from real video data captured with a hand-held camera, and show that the proposed weighting scheme is robust to motion deblurring errors. | en_US |
dc.description.sponsorship | Society for Imaging Science and Technology | en_US |
dc.description.sponsorship | SPIE | en_US |
dc.description.sponsorship | Google | en_US |
dc.description.sponsorship | Fairchild Imaging | en_US |
dc.description.sponsorship | Canon | en_US |
dc.language.iso | eng | en_US |
dc.publisher | SPIE | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Blind Super-Resolution | en_US |
dc.subject | Motion Blur | en_US |
dc.title | Super-resolution restoration of motion blurred images | en_US |
dc.type | conferenceObject | en_US |
dc.relation.ispartof | Conference on Digital Photography X | en_US |
dc.department | İstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü | en_US |
dc.authorid | 0000-0003-0779-9620 | en_US |
dc.identifier.volume | 9023 | en_US |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.identifier.doi | 10.1117/12.2038844 | en_US |