FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203827541> ?p ?o ?g. }

• W3203827541 endingPage "452" @default.
• W3203827541 startingPage "442" @default.
• W3203827541 abstract "Most existing face image Super-Resolution (SR) methods assume that the Low-Resolution (LR) images were artificially downsampled from High-Resolution (HR) images with bicubic interpolation. This operation changes the natural image characteristics and reduces noise. Hence, SR methods trained on such data most often fail to produce good results when applied to real LR images. To solve this problem, a novel framework for the generation of realistic LR/HR training pairs is proposed. The framework estimates realistic blur kernels, noise distributions, and JPEG compression artifacts to generate LR images with similar image characteristics as the ones in the source domain. This allows to train an SR model using high-quality face images as Ground-Truth (GT). For better perceptual quality, a Generative Adversarial Network (GAN) based SR model is used, where the commonly used VGG-loss [1] is exchanged with LPIPS-loss [2]. Experimental results on both real and artificially corrupted face images show that our method results in more detailed reconstructions with less noise compared to the existing State-of-the-Art (SoTA) methods. In addition, it is shown that the traditional non-reference Image Quality Assessment (IQA) methods fail to capture this improvement and demonstrate that the more recent NIMA metric [3] correlates better with human perception via Mean Opinion Rank (MOR)." @default.
• W3203827541 created "2021-10-11" @default.
• W3203827541 creator A5022176859 @default.
• W3203827541 creator A5041199606 @default.
• W3203827541 creator A5074373848 @default.
• W3203827541 date "2021-10-28" @default.
• W3203827541 modified "2023-10-17" @default.
• W3203827541 title "Real‐world super‐resolution of face‐images from surveillance cameras" @default.
• W3203827541 cites W1885185971 @default.
• W3203827541 cites W1982471090 @default.
• W3203827541 cites W2083610878 @default.
• W3203827541 cites W2099470017 @default.
• W3203827541 cites W2102166818 @default.
• W3203827541 cites W2123619251 @default.
• W3203827541 cites W2141631520 @default.
• W3203827541 cites W2150283722 @default.
• W3203827541 cites W2152131136 @default.
• W3203827541 cites W2157494358 @default.
• W3203827541 cites W2157920973 @default.
• W3203827541 cites W2214802144 @default.
• W3203827541 cites W2242218935 @default.
• W3203827541 cites W2331128040 @default.
• W3203827541 cites W2565312867 @default.
• W3203827541 cites W2571611310 @default.
• W3203827541 cites W2607041014 @default.
• W3203827541 cites W2741137940 @default.
• W3203827541 cites W2768814045 @default.
• W3203827541 cites W2798278116 @default.
• W3203827541 cites W2799120945 @default.
• W3203827541 cites W2883102461 @default.
• W3203827541 cites W2891158090 @default.
• W3203827541 cites W2962770929 @default.
• W3203827541 cites W2962785568 @default.
• W3203827541 cites W2962793481 @default.
• W3203827541 cites W2962814024 @default.
• W3203827541 cites W2963186101 @default.
• W3203827541 cites W2963372104 @default.
• W3203827541 cites W2963470893 @default.
• W3203827541 cites W2963583792 @default.
• W3203827541 cites W2963676087 @default.
• W3203827541 cites W2963704386 @default.
• W3203827541 cites W2963774720 @default.
• W3203827541 cites W2964060609 @default.
• W3203827541 cites W2972113259 @default.
• W3203827541 cites W2987150909 @default.
• W3203827541 cites W3009900215 @default.
• W3203827541 cites W3011043518 @default.
• W3203827541 cites W3011456574 @default.
• W3203827541 cites W3012322483 @default.
• W3203827541 cites W3034348762 @default.
• W3203827541 cites W3034352949 @default.
• W3203827541 cites W3034564595 @default.
• W3203827541 cites W3034785019 @default.
• W3203827541 cites W3035302306 @default.
• W3203827541 cites W3035304632 @default.
• W3203827541 cites W3103635814 @default.
• W3203827541 cites W3107811908 @default.
• W3203827541 doi "https://doi.org/10.1049/ipr2.12359" @default.
• W3203827541 hasPublicationYear "2021" @default.
• W3203827541 type Work @default.
• W3203827541 sameAs 3203827541 @default.
• W3203827541 citedByCount "9" @default.
• W3203827541 countsByYear W32038275412021 @default.
• W3203827541 countsByYear W32038275412022 @default.
• W3203827541 countsByYear W32038275412023 @default.
• W3203827541 crossrefType "journal-article" @default.
• W3203827541 hasAuthorship W3203827541A5022176859 @default.
• W3203827541 hasAuthorship W3203827541A5041199606 @default.
• W3203827541 hasAuthorship W3203827541A5074373848 @default.
• W3203827541 hasBestOaLocation W32038275411 @default.
• W3203827541 hasConcept C115961682 @default.
• W3203827541 hasConcept C137800194 @default.
• W3203827541 hasConcept C144024400 @default.
• W3203827541 hasConcept C146849305 @default.
• W3203827541 hasConcept C153180895 @default.
• W3203827541 hasConcept C154945302 @default.
• W3203827541 hasConcept C162324750 @default.
• W3203827541 hasConcept C171836373 @default.
• W3203827541 hasConcept C176217482 @default.
• W3203827541 hasConcept C21547014 @default.
• W3203827541 hasConcept C2779304628 @default.
• W3203827541 hasConcept C31972630 @default.
• W3203827541 hasConcept C36289849 @default.
• W3203827541 hasConcept C41008148 @default.
• W3203827541 hasConcept C49608258 @default.
• W3203827541 hasConcept C55020928 @default.
• W3203827541 hasConcept C62897895 @default.
• W3203827541 hasConcept C99498987 @default.
• W3203827541 hasConceptScore W3203827541C115961682 @default.
• W3203827541 hasConceptScore W3203827541C137800194 @default.
• W3203827541 hasConceptScore W3203827541C144024400 @default.
• W3203827541 hasConceptScore W3203827541C146849305 @default.
• W3203827541 hasConceptScore W3203827541C153180895 @default.
• W3203827541 hasConceptScore W3203827541C154945302 @default.
• W3203827541 hasConceptScore W3203827541C162324750 @default.
• W3203827541 hasConceptScore W3203827541C171836373 @default.
• W3203827541 hasConceptScore W3203827541C176217482 @default.
• W3203827541 hasConceptScore W3203827541C21547014 @default.

• next