Отрывок: 4, 1.6) GCC Glare color change Determines how the color of the glare changes from its center to the periph- ery. In our experiments has been cho- sen from range: (0.2, 1.8) MH Mask high The upper boundary on the value of mask. Has been set to 1 ML Mask low The lower boundary on the value of mask. In our experiments has been cho- sen from range: (0, 0.4) Input: I – source image Output: V – “veiled” image, GT – “ground truth” image. Part 1: Distance matrix computation 1.1: Random...
Полная запись метаданных
Поле DC | Значение | Язык |
---|---|---|
dc.contributor.author | Shoshin, A.V. | - |
dc.contributor.author | Shvets, E.A. | - |
dc.date.accessioned | 2021-08-17 12:54:30 | - |
dc.date.available | 2021-08-17 12:54:30 | - |
dc.date.issued | 2021-07 | - |
dc.identifier | Dspace\SGAU\20210805\90783 | ru |
dc.identifier.citation | Shoshin AV, Shvets EA. Veiling glare removal: synthetic dataset generation, metrics and neural network architecture. Computer Optics 2021; 45(4): 615-626. DOI: 10.18287/2412-6179-CO-883. | ru |
dc.identifier.uri | https://dx.doi.org/10.18287/2412-6179-CO-883 | - |
dc.identifier.uri | http://repo.ssau.ru/handle/Zhurnal-Komputernaya-optika/Veiling-glare-removal-synthetic-dataset-generation-metrics-and-neural-network-architecture-90783 | - |
dc.description.abstract | In photography, the presence of a bright light source often reduces the quality and readability of the resulting image. Light rays reflect and bounce off camera elements, sensor or diaphragm causing unwanted artifacts. These artifacts are generally known as "lens flare" and may have different influences on the photo: reduce contrast of the image (veiling glare), add circular or circular-like effects (ghosting flare), appear as bright rays spreading from light source (starburst pattern), or cause aberrations. All these effects are generally undesirable, as they reduce legibility and aesthetics of the image. In this paper we address the problem of removing or reducing the effect of veiling glare on the image. There are no available large-scale datasets for this problem and no established metrics, so we start by (i) proposing a simple and fast algorithm of generating synthetic veiling glare images necessary for training and (ii) studying metrics used in related image enhancement tasks (dehazing and underwater image enhancement). We select three such no-reference metrics (UCIQE, UIQM and CCF) and show that their improvement indicates better veil removal. Finally, we experiment on neural network architectures and propose a two-branched architecture and a training procedure utilizing structural similarity measure. | ru |
dc.language.iso | en_US | ru |
dc.publisher | Самарский национальный исследовательский университет | ru |
dc.relation.ispartofseries | 45;4 | - |
dc.subject | lens flare | ru |
dc.subject | veiling glare | ru |
dc.subject | image enhancement | ru |
dc.subject | deep learning | ru |
dc.subject | synthetic data | ru |
dc.title | Veiling glare removal: synthetic dataset generation, metrics and neural network architecture | ru |
dc.type | Article | ru |
dc.textpart | 4, 1.6) GCC Glare color change Determines how the color of the glare changes from its center to the periph- ery. In our experiments has been cho- sen from range: (0.2, 1.8) MH Mask high The upper boundary on the value of mask. Has been set to 1 ML Mask low The lower boundary on the value of mask. In our experiments has been cho- sen from range: (0, 0.4) Input: I – source image Output: V – “veiled” image, GT – “ground truth” image. Part 1: Distance matrix computation 1.1: Random... | - |
dc.classindex.scsti | 28.23.15, 28.23.37, 20.19.29 | - |
Располагается в коллекциях: | Журнал "Компьютерная оптика" |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
450417.pdf | Основная статья | 3.79 MB | Adobe PDF | Просмотреть/Открыть |
Показать базовое описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.