Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893749448> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2893749448 abstract "This paper proposes a deep learning architecture that attains statistically significant improvements over traditional algorithms in Poisson image denoising espically when the noise is strong. Poisson noise commonly occurs in low-light and photon- limited settings, where the noise can be most accurately modeled by the Poission distribution. Poisson noise traditionally prevails only in specific fields such as astronomical imaging. However, with the booming market of surveillance cameras, which commonly operate in low-light environments, or mobile phones, which produce noisy night scene pictures due to lower-grade sensors, the necessity for an advanced Poisson image denoising algorithm has increased. Deep learning has achieved amazing breakthroughs in other imaging problems, such image segmentation and recognition, and this paper proposes a deep learning denoising network that outperforms traditional algorithms in Poisson denoising especially when the noise is strong. The architecture incorporates a hybrid of convolutional and deconvolutional layers along with symmetric connections. The denoising network achieved statistically significant 0.38dB, 0.68dB, and 1.04dB average PSNR gains over benchmark traditional algorithms in experiments with image peak values 4, 2, and 1. The denoising network can also operate with shorter computational time while still outperforming the benchmark algorithm by tuning the reconstruction stride sizes." @default.
- W2893749448 created "2018-10-05" @default.
- W2893749448 creator A5008832723 @default.
- W2893749448 creator A5063076942 @default.
- W2893749448 date "2018-09-27" @default.
- W2893749448 modified "2023-09-27" @default.
- W2893749448 title "Image Reconstruction Using Deep Learning" @default.
- W2893749448 hasPublicationYear "2018" @default.
- W2893749448 type Work @default.
- W2893749448 sameAs 2893749448 @default.
- W2893749448 citedByCount "1" @default.
- W2893749448 countsByYear W28937494482019 @default.
- W2893749448 crossrefType "posted-content" @default.
- W2893749448 hasAuthorship W2893749448A5008832723 @default.
- W2893749448 hasAuthorship W2893749448A5063076942 @default.
- W2893749448 hasConcept C100906024 @default.
- W2893749448 hasConcept C105795698 @default.
- W2893749448 hasConcept C108583219 @default.
- W2893749448 hasConcept C11413529 @default.
- W2893749448 hasConcept C115961682 @default.
- W2893749448 hasConcept C13280743 @default.
- W2893749448 hasConcept C141379421 @default.
- W2893749448 hasConcept C153180895 @default.
- W2893749448 hasConcept C154945302 @default.
- W2893749448 hasConcept C163294075 @default.
- W2893749448 hasConcept C185798385 @default.
- W2893749448 hasConcept C205649164 @default.
- W2893749448 hasConcept C2983327147 @default.
- W2893749448 hasConcept C31972630 @default.
- W2893749448 hasConcept C33923547 @default.
- W2893749448 hasConcept C41008148 @default.
- W2893749448 hasConcept C72659945 @default.
- W2893749448 hasConcept C76155785 @default.
- W2893749448 hasConcept C81363708 @default.
- W2893749448 hasConcept C94915269 @default.
- W2893749448 hasConcept C99498987 @default.
- W2893749448 hasConceptScore W2893749448C100906024 @default.
- W2893749448 hasConceptScore W2893749448C105795698 @default.
- W2893749448 hasConceptScore W2893749448C108583219 @default.
- W2893749448 hasConceptScore W2893749448C11413529 @default.
- W2893749448 hasConceptScore W2893749448C115961682 @default.
- W2893749448 hasConceptScore W2893749448C13280743 @default.
- W2893749448 hasConceptScore W2893749448C141379421 @default.
- W2893749448 hasConceptScore W2893749448C153180895 @default.
- W2893749448 hasConceptScore W2893749448C154945302 @default.
- W2893749448 hasConceptScore W2893749448C163294075 @default.
- W2893749448 hasConceptScore W2893749448C185798385 @default.
- W2893749448 hasConceptScore W2893749448C205649164 @default.
- W2893749448 hasConceptScore W2893749448C2983327147 @default.
- W2893749448 hasConceptScore W2893749448C31972630 @default.
- W2893749448 hasConceptScore W2893749448C33923547 @default.
- W2893749448 hasConceptScore W2893749448C41008148 @default.
- W2893749448 hasConceptScore W2893749448C72659945 @default.
- W2893749448 hasConceptScore W2893749448C76155785 @default.
- W2893749448 hasConceptScore W2893749448C81363708 @default.
- W2893749448 hasConceptScore W2893749448C94915269 @default.
- W2893749448 hasConceptScore W2893749448C99498987 @default.
- W2893749448 hasLocation W28937494481 @default.
- W2893749448 hasOpenAccess W2893749448 @default.
- W2893749448 hasPrimaryLocation W28937494481 @default.
- W2893749448 hasRelatedWork W2028071053 @default.
- W2893749448 hasRelatedWork W2510850936 @default.
- W2893749448 hasRelatedWork W2890881262 @default.
- W2893749448 hasRelatedWork W2891246203 @default.
- W2893749448 hasRelatedWork W2907700557 @default.
- W2893749448 hasRelatedWork W2964549159 @default.
- W2893749448 hasRelatedWork W3022360179 @default.
- W2893749448 hasRelatedWork W3047520925 @default.
- W2893749448 hasRelatedWork W3081181294 @default.
- W2893749448 hasRelatedWork W3091865411 @default.
- W2893749448 hasRelatedWork W3108061235 @default.
- W2893749448 hasRelatedWork W3108413618 @default.
- W2893749448 hasRelatedWork W3114171168 @default.
- W2893749448 hasRelatedWork W3126582326 @default.
- W2893749448 hasRelatedWork W3126781302 @default.
- W2893749448 hasRelatedWork W3129492101 @default.
- W2893749448 hasRelatedWork W3168541514 @default.
- W2893749448 hasRelatedWork W3198202938 @default.
- W2893749448 hasRelatedWork W3201788907 @default.
- W2893749448 hasRelatedWork W2185459662 @default.
- W2893749448 isParatext "false" @default.
- W2893749448 isRetracted "false" @default.
- W2893749448 magId "2893749448" @default.
- W2893749448 workType "article" @default.