Matches in SemOpenAlex for { <https://semopenalex.org/work/W3038139892> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3038139892 endingPage "3501" @default.
- W3038139892 startingPage "3486" @default.
- W3038139892 abstract "Convolutional Neural Networks (CNN)-based approaches have shown promising results in pansharpening of satellite images in recent years. However, they still exhibit limitations in producing high-quality pansharpening outputs. To that end, we propose a new self-supervised learning framework, where we treat pansharpening as a colorization problem, which brings an entirely novel perspective and solution to the problem compared to existing methods that base their solution solely on producing a super-resolution version of the multispectral image. Whereas CNN-based methods provide a reduced resolution panchromatic image as input to their model along with reduced resolution multispectral images, hence learn to increase their resolution together, we instead provide the grayscale transformed multispectral image as input, and train our model to learn the colorization of the grayscale input. We further address the fixed downscale ratio assumption during training, which does not generalize well to the full-resolution scenario. We introduce a noise injection into the training by randomly varying the downsampling ratios. Those two critical changes, along with the addition of adversarial training in the proposed PanColorization Generative Adversarial Networks (PanColorGAN) framework, help overcome the spatial detail loss and blur problems that are observed in CNN-based pansharpening. The proposed approach outperforms the previous CNN-based and traditional methods as demonstrated in our experiments." @default.
- W3038139892 created "2020-07-10" @default.
- W3038139892 creator A5009545581 @default.
- W3038139892 creator A5024107070 @default.
- W3038139892 creator A5041935848 @default.
- W3038139892 creator A5063739673 @default.
- W3038139892 date "2021-04-01" @default.
- W3038139892 modified "2023-09-30" @default.
- W3038139892 title "Rethinking CNN-Based Pansharpening: Guided Colorization of Panchromatic Images via GANs" @default.
- W3038139892 cites W1943127271 @default.
- W3038139892 cites W1980110630 @default.
- W3038139892 cites W1991460509 @default.
- W3038139892 cites W2120053475 @default.
- W3038139892 cites W2124743705 @default.
- W3038139892 cites W2139529730 @default.
- W3038139892 cites W2154789478 @default.
- W3038139892 cites W2159269332 @default.
- W3038139892 cites W2163334907 @default.
- W3038139892 cites W2163677711 @default.
- W3038139892 cites W2171108951 @default.
- W3038139892 cites W2171211028 @default.
- W3038139892 cites W2172185514 @default.
- W3038139892 cites W2462592242 @default.
- W3038139892 cites W2519236071 @default.
- W3038139892 cites W2619662254 @default.
- W3038139892 cites W2700882095 @default.
- W3038139892 cites W2737219040 @default.
- W3038139892 cites W2777033955 @default.
- W3038139892 cites W2782522152 @default.
- W3038139892 cites W2792142731 @default.
- W3038139892 cites W2806865914 @default.
- W3038139892 cites W2920844353 @default.
- W3038139892 cites W2963073614 @default.
- W3038139892 cites W2963470893 @default.
- W3038139892 cites W2963695810 @default.
- W3038139892 cites W2964275574 @default.
- W3038139892 cites W3001742927 @default.
- W3038139892 cites W3098542449 @default.
- W3038139892 cites W3102726805 @default.
- W3038139892 doi "https://doi.org/10.1109/tgrs.2020.3010441" @default.
- W3038139892 hasPublicationYear "2021" @default.
- W3038139892 type Work @default.
- W3038139892 sameAs 3038139892 @default.
- W3038139892 citedByCount "43" @default.
- W3038139892 countsByYear W30381398922021 @default.
- W3038139892 countsByYear W30381398922022 @default.
- W3038139892 countsByYear W30381398922023 @default.
- W3038139892 crossrefType "journal-article" @default.
- W3038139892 hasAuthorship W3038139892A5009545581 @default.
- W3038139892 hasAuthorship W3038139892A5024107070 @default.
- W3038139892 hasAuthorship W3038139892A5041935848 @default.
- W3038139892 hasAuthorship W3038139892A5063739673 @default.
- W3038139892 hasBestOaLocation W30381398922 @default.
- W3038139892 hasConcept C107445234 @default.
- W3038139892 hasConcept C110384440 @default.
- W3038139892 hasConcept C115961682 @default.
- W3038139892 hasConcept C153180895 @default.
- W3038139892 hasConcept C154945302 @default.
- W3038139892 hasConcept C173163844 @default.
- W3038139892 hasConcept C205372480 @default.
- W3038139892 hasConcept C31972630 @default.
- W3038139892 hasConcept C41008148 @default.
- W3038139892 hasConcept C78201319 @default.
- W3038139892 hasConcept C81363708 @default.
- W3038139892 hasConceptScore W3038139892C107445234 @default.
- W3038139892 hasConceptScore W3038139892C110384440 @default.
- W3038139892 hasConceptScore W3038139892C115961682 @default.
- W3038139892 hasConceptScore W3038139892C153180895 @default.
- W3038139892 hasConceptScore W3038139892C154945302 @default.
- W3038139892 hasConceptScore W3038139892C173163844 @default.
- W3038139892 hasConceptScore W3038139892C205372480 @default.
- W3038139892 hasConceptScore W3038139892C31972630 @default.
- W3038139892 hasConceptScore W3038139892C41008148 @default.
- W3038139892 hasConceptScore W3038139892C78201319 @default.
- W3038139892 hasConceptScore W3038139892C81363708 @default.
- W3038139892 hasIssue "4" @default.
- W3038139892 hasLocation W30381398921 @default.
- W3038139892 hasLocation W30381398922 @default.
- W3038139892 hasOpenAccess W3038139892 @default.
- W3038139892 hasPrimaryLocation W30381398921 @default.
- W3038139892 hasRelatedWork W2004913087 @default.
- W3038139892 hasRelatedWork W2090346739 @default.
- W3038139892 hasRelatedWork W2418010961 @default.
- W3038139892 hasRelatedWork W2891330445 @default.
- W3038139892 hasRelatedWork W2900929188 @default.
- W3038139892 hasRelatedWork W2961060159 @default.
- W3038139892 hasRelatedWork W2984547193 @default.
- W3038139892 hasRelatedWork W3014967571 @default.
- W3038139892 hasRelatedWork W3038139892 @default.
- W3038139892 hasRelatedWork W3121005460 @default.
- W3038139892 hasVolume "59" @default.
- W3038139892 isParatext "false" @default.
- W3038139892 isRetracted "false" @default.
- W3038139892 magId "3038139892" @default.
- W3038139892 workType "article" @default.