Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295137228> ?p ?o ?g. }
- W4295137228 endingPage "103626" @default.
- W4295137228 startingPage "103626" @default.
- W4295137228 abstract "While many efforts have been devoted to addressing image denoising and achieve continuously improving results during the past few decades, it is fair to say that no a stand-alone method is consistently better than others. Nonetheless, many existing denoising methods, each having a different denoising capability, can yield various but complementary denoised images with respect to specific local areas. To effectively exploit the complementarity and diversity among the denoised images obtained with different denoisers, in this work we fuse them to produce an overall better result, which is fundamental to achieve robust and competitive denoising performance especially for complex scenes. A framework called deep fusion network (DFNet) is proposed to generate a consistent estimation about the final denoised image, taking advantage of the complementarity of denoisers and suppressing the bias. Specifically, given a noisy image, we first exploit a set of representative image denoisers to denoise it respectively, and obtain the corresponding initial denoised images. Then these initial denoised images are concatenated and fed into the proposed DFNet, and the proposed DFNet seeks to adjust its network parameters to produce the fused image (as the final denoised image) with an unsupervised training strategy through minimizing the carefully designed loss function. The experimental results show that our approach outperforms the stand-alone methods as well as the ones using combination strategy by large margin both in objective and subjective evaluations. Compared to the those methods that are relatively close to our strategy, the proposed DFNet is extensible and parameter free, which means it can cope with a variable number of different denoisers and avoid the manual intervention during the fusion process. The proposed DFNet has greater flexibility and better practicality." @default.
- W4295137228 created "2022-09-11" @default.
- W4295137228 creator A5029842958 @default.
- W4295137228 creator A5032148962 @default.
- W4295137228 creator A5042276980 @default.
- W4295137228 creator A5043984114 @default.
- W4295137228 creator A5077441033 @default.
- W4295137228 date "2022-10-01" @default.
- W4295137228 modified "2023-10-16" @default.
- W4295137228 title "An unsupervised fusion network for boosting denoising performance" @default.
- W4295137228 cites W1901129140 @default.
- W4295137228 cites W1978749115 @default.
- W4295137228 cites W2048695508 @default.
- W4295137228 cites W2056370875 @default.
- W4295137228 cites W2102166818 @default.
- W4295137228 cites W2508457857 @default.
- W4295137228 cites W2590560192 @default.
- W4295137228 cites W2804946145 @default.
- W4295137228 cites W2963446712 @default.
- W4295137228 cites W2963725279 @default.
- W4295137228 cites W2998841120 @default.
- W4295137228 cites W3011455439 @default.
- W4295137228 cites W3033562919 @default.
- W4295137228 cites W3033920316 @default.
- W4295137228 cites W3035542568 @default.
- W4295137228 cites W3041734050 @default.
- W4295137228 cites W3048092834 @default.
- W4295137228 cites W3077327398 @default.
- W4295137228 cites W3087110941 @default.
- W4295137228 cites W3092019704 @default.
- W4295137228 cites W3104725225 @default.
- W4295137228 cites W3125869362 @default.
- W4295137228 cites W3128141137 @default.
- W4295137228 cites W3154061064 @default.
- W4295137228 cites W3174829522 @default.
- W4295137228 cites W3175028147 @default.
- W4295137228 cites W3177553843 @default.
- W4295137228 cites W3185318678 @default.
- W4295137228 cites W3205329422 @default.
- W4295137228 cites W4200282803 @default.
- W4295137228 cites W4205933526 @default.
- W4295137228 cites W4210469012 @default.
- W4295137228 cites W4214577770 @default.
- W4295137228 cites W4214744659 @default.
- W4295137228 doi "https://doi.org/10.1016/j.jvcir.2022.103626" @default.
- W4295137228 hasPublicationYear "2022" @default.
- W4295137228 type Work @default.
- W4295137228 citedByCount "1" @default.
- W4295137228 countsByYear W42951372282022 @default.
- W4295137228 crossrefType "journal-article" @default.
- W4295137228 hasAuthorship W4295137228A5029842958 @default.
- W4295137228 hasAuthorship W4295137228A5032148962 @default.
- W4295137228 hasAuthorship W4295137228A5042276980 @default.
- W4295137228 hasAuthorship W4295137228A5043984114 @default.
- W4295137228 hasAuthorship W4295137228A5077441033 @default.
- W4295137228 hasConcept C115961682 @default.
- W4295137228 hasConcept C119857082 @default.
- W4295137228 hasConcept C153180895 @default.
- W4295137228 hasConcept C154945302 @default.
- W4295137228 hasConcept C163294075 @default.
- W4295137228 hasConcept C165696696 @default.
- W4295137228 hasConcept C202269582 @default.
- W4295137228 hasConcept C2983327147 @default.
- W4295137228 hasConcept C38652104 @default.
- W4295137228 hasConcept C41008148 @default.
- W4295137228 hasConcept C46686674 @default.
- W4295137228 hasConcept C54355233 @default.
- W4295137228 hasConcept C69744172 @default.
- W4295137228 hasConcept C774472 @default.
- W4295137228 hasConcept C86803240 @default.
- W4295137228 hasConceptScore W4295137228C115961682 @default.
- W4295137228 hasConceptScore W4295137228C119857082 @default.
- W4295137228 hasConceptScore W4295137228C153180895 @default.
- W4295137228 hasConceptScore W4295137228C154945302 @default.
- W4295137228 hasConceptScore W4295137228C163294075 @default.
- W4295137228 hasConceptScore W4295137228C165696696 @default.
- W4295137228 hasConceptScore W4295137228C202269582 @default.
- W4295137228 hasConceptScore W4295137228C2983327147 @default.
- W4295137228 hasConceptScore W4295137228C38652104 @default.
- W4295137228 hasConceptScore W4295137228C41008148 @default.
- W4295137228 hasConceptScore W4295137228C46686674 @default.
- W4295137228 hasConceptScore W4295137228C54355233 @default.
- W4295137228 hasConceptScore W4295137228C69744172 @default.
- W4295137228 hasConceptScore W4295137228C774472 @default.
- W4295137228 hasConceptScore W4295137228C86803240 @default.
- W4295137228 hasLocation W42951372281 @default.
- W4295137228 hasOpenAccess W4295137228 @default.
- W4295137228 hasPrimaryLocation W42951372281 @default.
- W4295137228 hasRelatedWork W2003125512 @default.
- W4295137228 hasRelatedWork W2010832783 @default.
- W4295137228 hasRelatedWork W2082361748 @default.
- W4295137228 hasRelatedWork W2350476422 @default.
- W4295137228 hasRelatedWork W2376679277 @default.
- W4295137228 hasRelatedWork W2378252746 @default.
- W4295137228 hasRelatedWork W2380182722 @default.
- W4295137228 hasRelatedWork W3033920316 @default.
- W4295137228 hasRelatedWork W3133004360 @default.
- W4295137228 hasRelatedWork W4221052466 @default.