FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903622424> ?p ?o ?g. }

• W2903622424 endingPage "2330" @default.
• W2903622424 startingPage "2319" @default.
• W2903622424 abstract "Light field (LF) photography is an emerging paradigm for capturing more immersive representations of the real world. However, arising from the inherent tradeoff between the angular and spatial dimensions, the spatial resolution of LF images captured by commercial micro-lens-based LF cameras is significantly constrained. In this paper, we propose effective and efficient end-to-end convolutional neural network models for spatially super-resolving LF images. Specifically, the proposed models have an hourglass shape, which allows feature extraction to be performed at the low-resolution level to save both the computational and memory costs. To fully make use of the 4D structure information of LF data in both the spatial and angular domains, we propose to use 4D convolution to characterize the relationship among pixels. Moreover, as an approximation of 4D convolution, we also propose to use spatial-angular separable (SAS) convolutions for more computationally and memory-efficient extraction of spatial-angular joint features. Extensive experimental results on 57 test LF images with various challenging natural scenes show significant advantages from the proposed models over the state-of-the-art methods. That is, an average PSNR gain of more than 3.0 dB and better visual quality are achieved, and our methods preserve the LF structure of the super-resolved LF images better, which is highly desirable for subsequent applications. In addition, the SAS convolution-based model can achieve three times speed up with only negligible reconstruction quality decrease when compared with the 4D convolution-based one. The source code of our method is available online." @default.
• W2903622424 created "2018-12-22" @default.
• W2903622424 creator A5010479652 @default.
• W2903622424 creator A5031957432 @default.
• W2903622424 creator A5045843249 @default.
• W2903622424 creator A5064527448 @default.
• W2903622424 creator A5079572598 @default.
• W2903622424 creator A5089713015 @default.
• W2903622424 date "2019-05-01" @default.
• W2903622424 modified "2023-10-05" @default.
• W2903622424 title "Light Field Spatial Super-Resolution Using Deep Efficient Spatial-Angular Separable Convolution" @default.
• W2903622424 cites W1599195847 @default.
• W2903622424 cites W1677182931 @default.
• W2903622424 cites W1914596733 @default.
• W2903622424 cites W1963882359 @default.
• W2903622424 cites W1974973438 @default.
• W2903622424 cites W1976598894 @default.
• W2903622424 cites W1977581467 @default.
• W2903622424 cites W1992367866 @default.
• W2903622424 cites W2014693452 @default.
• W2903622424 cites W2038323587 @default.
• W2903622424 cites W2042687553 @default.
• W2903622424 cites W2067827172 @default.
• W2903622424 cites W2093381227 @default.
• W2903622424 cites W2105198794 @default.
• W2903622424 cites W2119967924 @default.
• W2903622424 cites W2133665775 @default.
• W2903622424 cites W2143050242 @default.
• W2903622424 cites W2150007820 @default.
• W2903622424 cites W2239879258 @default.
• W2903622424 cites W2242218935 @default.
• W2903622424 cites W2342431481 @default.
• W2903622424 cites W2345303319 @default.
• W2903622424 cites W2476548250 @default.
• W2903622424 cites W2509310573 @default.
• W2903622424 cites W2516928329 @default.
• W2903622424 cites W2531327760 @default.
• W2903622424 cites W2551052086 @default.
• W2903622424 cites W2572840108 @default.
• W2903622424 cites W2588196171 @default.
• W2903622424 cites W2607041014 @default.
• W2903622424 cites W2753246299 @default.
• W2903622424 cites W2753630964 @default.
• W2903622424 cites W2792891339 @default.
• W2903622424 cites W2964251418 @default.
• W2903622424 cites W3098172517 @default.
• W2903622424 cites W3100465609 @default.
• W2903622424 cites W3104468713 @default.
• W2903622424 doi "https://doi.org/10.1109/tip.2018.2885236" @default.
• W2903622424 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30530364" @default.
• W2903622424 hasPublicationYear "2019" @default.
• W2903622424 type Work @default.
• W2903622424 sameAs 2903622424 @default.
• W2903622424 citedByCount "115" @default.
• W2903622424 countsByYear W29036224242019 @default.
• W2903622424 countsByYear W29036224242020 @default.
• W2903622424 countsByYear W29036224242021 @default.
• W2903622424 countsByYear W29036224242022 @default.
• W2903622424 countsByYear W29036224242023 @default.
• W2903622424 crossrefType "journal-article" @default.
• W2903622424 hasAuthorship W2903622424A5010479652 @default.
• W2903622424 hasAuthorship W2903622424A5031957432 @default.
• W2903622424 hasAuthorship W2903622424A5045843249 @default.
• W2903622424 hasAuthorship W2903622424A5064527448 @default.
• W2903622424 hasAuthorship W2903622424A5079572598 @default.
• W2903622424 hasAuthorship W2903622424A5089713015 @default.
• W2903622424 hasConcept C11413529 @default.
• W2903622424 hasConcept C153180895 @default.
• W2903622424 hasConcept C154945302 @default.
• W2903622424 hasConcept C160633673 @default.
• W2903622424 hasConcept C202444582 @default.
• W2903622424 hasConcept C205372480 @default.
• W2903622424 hasConcept C31972630 @default.
• W2903622424 hasConcept C33923547 @default.
• W2903622424 hasConcept C41008148 @default.
• W2903622424 hasConcept C45347329 @default.
• W2903622424 hasConcept C50644808 @default.
• W2903622424 hasConcept C52622490 @default.
• W2903622424 hasConcept C81363708 @default.
• W2903622424 hasConcept C9652623 @default.
• W2903622424 hasConceptScore W2903622424C11413529 @default.
• W2903622424 hasConceptScore W2903622424C153180895 @default.
• W2903622424 hasConceptScore W2903622424C154945302 @default.
• W2903622424 hasConceptScore W2903622424C160633673 @default.
• W2903622424 hasConceptScore W2903622424C202444582 @default.
• W2903622424 hasConceptScore W2903622424C205372480 @default.
• W2903622424 hasConceptScore W2903622424C31972630 @default.
• W2903622424 hasConceptScore W2903622424C33923547 @default.
• W2903622424 hasConceptScore W2903622424C41008148 @default.
• W2903622424 hasConceptScore W2903622424C45347329 @default.
• W2903622424 hasConceptScore W2903622424C50644808 @default.
• W2903622424 hasConceptScore W2903622424C52622490 @default.
• W2903622424 hasConceptScore W2903622424C81363708 @default.
• W2903622424 hasConceptScore W2903622424C9652623 @default.
• W2903622424 hasFunder F4320321001 @default.
• W2903622424 hasIssue "5" @default.
• W2903622424 hasLocation W29036224241 @default.
• W2903622424 hasLocation W29036224242 @default.

• next