FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205836451> ?p ?o ?g. }

• W4205836451 endingPage "16" @default.
• W4205836451 startingPage "1" @default.
• W4205836451 abstract "Pansharpening exploits the high-spatial-resolution panchromatic (HR PAN) images to restore the spatial resolution of the corresponding low-spatial-resolution multi-spectral (LR MS) image, producing a fused image and high-spatial-resolution multi-spectral (HR MS) image. Recently, many methods based on convolutional neural networks (CNNs) have been put forth for the pansharpening task, but most of them still have some limitations, such as the simple stacked convolutional architectures resulting in information distortion, and some scale-related problems caused by the supervised learning strategy. Therefore, we propose a method named super-resolution iterative residual (SRIR) network with a cross-scale (CS) learning strategy to overcome these drawbacks. Regarding the SRIR we propose, we design an upsampling network based on a sub-pixel convolution structure to replace the traditional upsampling pre-processing. We adopt the iterative networks framework and design a new spatial information injection module to continuously inject spatial and spectral features into the network, which can enhance the information flow and transmission. We produce approximate HR MS with a guidance filter and map the residual information between the approximate HR MS and the reference HR MS by SRIR to enhance the quality of fused images. Regarding the CS we propose, we train the network at degraded scale, which is named deep prior, and then design a finer-scale unsupervised fine-tuning loss function to refine the network parameters with deep priors, to overcome the scale effect. Experiments show the following: 1) SRIR-based pansharpening method can obtain the best result at the degraded scale; 2) the scale-effect is negatively correlated with the depth of the network, meaning that the deeper the network, the stronger the robustness to scale effect; 3) the CS learning strategy can widely improve the performance of CNNs-based pansharpening methods in full-resolution; and 4) our method can produce better results at full-resolution scale than all the other traditional and deep learning methods." @default.
• W4205836451 created "2022-01-26" @default.
• W4205836451 creator A5003004826 @default.
• W4205836451 creator A5027883397 @default.
• W4205836451 creator A5073581902 @default.
• W4205836451 date "2022-01-01" @default.
• W4205836451 modified "2023-09-24" @default.
• W4205836451 title "Pansharpening via Super-Resolution Iterative Residual Network With a Cross-Scale Learning Strategy" @default.
• W4205836451 cites W1543978614 @default.
• W4205836451 cites W1885185971 @default.
• W4205836451 cites W2010515061 @default.
• W4205836451 cites W2064366277 @default.
• W4205836451 cites W2094691487 @default.
• W4205836451 cites W2120053475 @default.
• W4205836451 cites W2120878985 @default.
• W4205836451 cites W2125188192 @default.
• W4205836451 cites W2150630348 @default.
• W4205836451 cites W2153502929 @default.
• W4205836451 cites W2154789478 @default.
• W4205836451 cites W2163677711 @default.
• W4205836451 cites W2171108951 @default.
• W4205836451 cites W2172185514 @default.
• W4205836451 cites W2289534791 @default.
• W4205836451 cites W2314528731 @default.
• W4205836451 cites W2339428543 @default.
• W4205836451 cites W2345211892 @default.
• W4205836451 cites W2462592242 @default.
• W4205836451 cites W2476548250 @default.
• W4205836451 cites W2616590213 @default.
• W4205836451 cites W2765749804 @default.
• W4205836451 cites W2775207294 @default.
• W4205836451 cites W2792114281 @default.
• W4205836451 cites W2792142731 @default.
• W4205836451 cites W2792365373 @default.
• W4205836451 cites W2807567802 @default.
• W4205836451 cites W2809372634 @default.
• W4205836451 cites W2891914057 @default.
• W4205836451 cites W2896986853 @default.
• W4205836451 cites W2921660688 @default.
• W4205836451 cites W2922407270 @default.
• W4205836451 cites W2935896423 @default.
• W4205836451 cites W2952004563 @default.
• W4205836451 cites W2953478519 @default.
• W4205836451 cites W2963183385 @default.
• W4205836451 cites W2963372104 @default.
• W4205836451 cites W2965814782 @default.
• W4205836451 cites W2978331778 @default.
• W4205836451 cites W2980358775 @default.
• W4205836451 cites W2983594732 @default.
• W4205836451 cites W2983856946 @default.
• W4205836451 cites W2989066465 @default.
• W4205836451 cites W2989264312 @default.
• W4205836451 cites W3001742927 @default.
• W4205836451 cites W3015046886 @default.
• W4205836451 cites W3019893222 @default.
• W4205836451 cites W3027778336 @default.
• W4205836451 cites W3029812440 @default.
• W4205836451 cites W3033344017 @default.
• W4205836451 cites W3036961641 @default.
• W4205836451 cites W3038139892 @default.
• W4205836451 cites W3041178351 @default.
• W4205836451 cites W3081397212 @default.
• W4205836451 cites W3097824737 @default.
• W4205836451 cites W3098542449 @default.
• W4205836451 cites W3099258777 @default.
• W4205836451 cites W3115223653 @default.
• W4205836451 doi "https://doi.org/10.1109/tgrs.2021.3138096" @default.
• W4205836451 hasPublicationYear "2022" @default.
• W4205836451 type Work @default.
• W4205836451 citedByCount "1" @default.
• W4205836451 countsByYear W42058364512023 @default.
• W4205836451 crossrefType "journal-article" @default.
• W4205836451 hasAuthorship W4205836451A5003004826 @default.
• W4205836451 hasAuthorship W4205836451A5027883397 @default.
• W4205836451 hasAuthorship W4205836451A5073581902 @default.
• W4205836451 hasConcept C110384440 @default.
• W4205836451 hasConcept C11413529 @default.
• W4205836451 hasConcept C115961682 @default.
• W4205836451 hasConcept C153180895 @default.
• W4205836451 hasConcept C154945302 @default.
• W4205836451 hasConcept C155512373 @default.
• W4205836451 hasConcept C160633673 @default.
• W4205836451 hasConcept C205372480 @default.
• W4205836451 hasConcept C31972630 @default.
• W4205836451 hasConcept C41008148 @default.
• W4205836451 hasConcept C45347329 @default.
• W4205836451 hasConcept C50644808 @default.
• W4205836451 hasConcept C81363708 @default.
• W4205836451 hasConceptScore W4205836451C110384440 @default.
• W4205836451 hasConceptScore W4205836451C11413529 @default.
• W4205836451 hasConceptScore W4205836451C115961682 @default.
• W4205836451 hasConceptScore W4205836451C153180895 @default.
• W4205836451 hasConceptScore W4205836451C154945302 @default.
• W4205836451 hasConceptScore W4205836451C155512373 @default.
• W4205836451 hasConceptScore W4205836451C160633673 @default.
• W4205836451 hasConceptScore W4205836451C205372480 @default.
• W4205836451 hasConceptScore W4205836451C31972630 @default.
• W4205836451 hasConceptScore W4205836451C41008148 @default.

• next