Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313244902> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4313244902 endingPage "251" @default.
- W4313244902 startingPage "251" @default.
- W4313244902 abstract "Numerous old images and videos were captured and stored under unfavorable conditions. Hence, old images and videos have uncertain and different noise patterns compared with those of modern ones. Denoising old images is an effective technique for reconstructing a clean image containing crucial information. However, obtaining noisy-clean image pairs for denoising old images is difficult and challenging for supervised learning. Preparing such a pair is expensive and burdensome, as existing denoising approaches require a considerable number of noisy-clean image pairs. To address this issue, we propose a robust noise-generation generative adversarial network (NG-GAN) that utilizes unpaired datasets to replicate the noise distribution of degraded old images inspired by the CycleGAN model. In our proposed method, the perception-based image quality evaluator metric is used to control noise generation effectively. An unpaired dataset is generated by selecting clean images with features that match the old images to train the proposed model. Experimental results demonstrate that the dataset generated by our proposed NG-GAN can better train state-of-the-art denoising models by effectively denoising old videos. The denoising models exhibit significantly improved peak signal-to-noise ratios and structural similarity index measures of 0.37 dB and 0.06 on average, respectively, on the dataset generated by our proposed NG-GAN." @default.
- W4313244902 created "2023-01-06" @default.
- W4313244902 creator A5051083488 @default.
- W4313244902 creator A5088699992 @default.
- W4313244902 date "2022-12-26" @default.
- W4313244902 modified "2023-10-14" @default.
- W4313244902 title "NG-GAN: A Robust Noise-Generation Generative Adversarial Network for Generating Old-Image Noise" @default.
- W4313244902 cites W2037642501 @default.
- W4313244902 cites W2048695508 @default.
- W4313244902 cites W2056370875 @default.
- W4313244902 cites W2083610878 @default.
- W4313244902 cites W2275363859 @default.
- W4313244902 cites W2331128040 @default.
- W4313244902 cites W2508457857 @default.
- W4313244902 cites W2562637781 @default.
- W4313244902 cites W2613155248 @default.
- W4313244902 cites W2741137940 @default.
- W4313244902 cites W2798278116 @default.
- W4313244902 cites W2799192307 @default.
- W4313244902 cites W2894629025 @default.
- W4313244902 cites W2902857081 @default.
- W4313244902 cites W2953823547 @default.
- W4313244902 cites W2962767526 @default.
- W4313244902 cites W2962793481 @default.
- W4313244902 cites W2963073614 @default.
- W4313244902 cites W2963255313 @default.
- W4313244902 cites W2963444790 @default.
- W4313244902 cites W2963725279 @default.
- W4313244902 cites W2964046397 @default.
- W4313244902 cites W2989193306 @default.
- W4313244902 cites W3000775737 @default.
- W4313244902 cites W3034239311 @default.
- W4313244902 cites W3034552520 @default.
- W4313244902 cites W3034598912 @default.
- W4313244902 cites W3102015846 @default.
- W4313244902 cites W3104725225 @default.
- W4313244902 cites W3146366485 @default.
- W4313244902 cites W3157035436 @default.
- W4313244902 cites W3171613875 @default.
- W4313244902 cites W3176148916 @default.
- W4313244902 cites W3188225995 @default.
- W4313244902 cites W3204358387 @default.
- W4313244902 cites W4226277663 @default.
- W4313244902 doi "https://doi.org/10.3390/s23010251" @default.
- W4313244902 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36616850" @default.
- W4313244902 hasPublicationYear "2022" @default.
- W4313244902 type Work @default.
- W4313244902 citedByCount "0" @default.
- W4313244902 crossrefType "journal-article" @default.
- W4313244902 hasAuthorship W4313244902A5051083488 @default.
- W4313244902 hasAuthorship W4313244902A5088699992 @default.
- W4313244902 hasBestOaLocation W43132449021 @default.
- W4313244902 hasConcept C103278499 @default.
- W4313244902 hasConcept C115961682 @default.
- W4313244902 hasConcept C153180895 @default.
- W4313244902 hasConcept C154945302 @default.
- W4313244902 hasConcept C163294075 @default.
- W4313244902 hasConcept C202474056 @default.
- W4313244902 hasConcept C23431618 @default.
- W4313244902 hasConcept C30814859 @default.
- W4313244902 hasConcept C31972630 @default.
- W4313244902 hasConcept C41008148 @default.
- W4313244902 hasConcept C65483669 @default.
- W4313244902 hasConcept C99498987 @default.
- W4313244902 hasConceptScore W4313244902C103278499 @default.
- W4313244902 hasConceptScore W4313244902C115961682 @default.
- W4313244902 hasConceptScore W4313244902C153180895 @default.
- W4313244902 hasConceptScore W4313244902C154945302 @default.
- W4313244902 hasConceptScore W4313244902C163294075 @default.
- W4313244902 hasConceptScore W4313244902C202474056 @default.
- W4313244902 hasConceptScore W4313244902C23431618 @default.
- W4313244902 hasConceptScore W4313244902C30814859 @default.
- W4313244902 hasConceptScore W4313244902C31972630 @default.
- W4313244902 hasConceptScore W4313244902C41008148 @default.
- W4313244902 hasConceptScore W4313244902C65483669 @default.
- W4313244902 hasConceptScore W4313244902C99498987 @default.
- W4313244902 hasFunder F4320322120 @default.
- W4313244902 hasIssue "1" @default.
- W4313244902 hasLocation W43132449021 @default.
- W4313244902 hasLocation W43132449022 @default.
- W4313244902 hasLocation W43132449023 @default.
- W4313244902 hasLocation W43132449024 @default.
- W4313244902 hasOpenAccess W4313244902 @default.
- W4313244902 hasPrimaryLocation W43132449021 @default.
- W4313244902 hasRelatedWork W2005185696 @default.
- W4313244902 hasRelatedWork W2081458845 @default.
- W4313244902 hasRelatedWork W2092957489 @default.
- W4313244902 hasRelatedWork W2130228941 @default.
- W4313244902 hasRelatedWork W2132132164 @default.
- W4313244902 hasRelatedWork W2143438001 @default.
- W4313244902 hasRelatedWork W2161229648 @default.
- W4313244902 hasRelatedWork W2235753890 @default.
- W4313244902 hasRelatedWork W2483420468 @default.
- W4313244902 hasRelatedWork W2993674027 @default.
- W4313244902 hasVolume "23" @default.
- W4313244902 isParatext "false" @default.
- W4313244902 isRetracted "false" @default.
- W4313244902 workType "article" @default.