FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306292690> ?p ?o ?g. }

• W4306292690 endingPage "242" @default.
• W4306292690 startingPage "215" @default.
• W4306292690 abstract "Guided image super-resolution (GISR) aims to obtain a high-resolution (HR) target image by enhancing the spatial resolution of a low-resolution (LR) target image under the guidance of a HR image. However, previous model-based methods mainly take the entire image as a whole, and assume the prior distribution between the HR target image and the HR guidance image, simply ignoring many non-local common characteristics between them. To alleviate this issue, we firstly propose a maximum a posteriori (MAP) estimation model for GISR with two types of priors on the HR target image, i.e., local implicit prior and global implicit prior. The local implicit prior aims to model the complex relationship between the HR target image and the HR guidance image from a local perspective, and the global implicit prior considers the non-local auto-regression property between the two images from a global perspective. Secondly, we design a novel alternating optimization algorithm to solve this model for GISR. The algorithm is in a concise framework that facilitates to be replicated into commonly used deep network structures. Thirdly, to reduce the information loss across iterative stages, the persistent memory mechanism is introduced to augment the information representation by exploiting the Long short-term memory unit (LSTM) in the image and feature spaces. In this way, a deep network with certain interpretation and high representation ability is built. Extensive experimental results validate the superiority of our method on a variety of GISR tasks, including Pan-sharpening, depth image super-resolution, and MR image super-resolution. Code will be released at https://github.com/manman1995/pansharpening ." @default.
• W4306292690 created "2022-10-15" @default.
• W4306292690 creator A5004164569 @default.
• W4306292690 creator A5020858452 @default.
• W4306292690 creator A5028103486 @default.
• W4306292690 creator A5057999649 @default.
• W4306292690 creator A5062166339 @default.
• W4306292690 creator A5079590055 @default.
• W4306292690 date "2022-10-15" @default.
• W4306292690 modified "2023-10-17" @default.
• W4306292690 title "Memory-Augmented Deep Unfolding Network for Guided Image Super-resolution" @default.
• W4306292690 cites W125693051 @default.
• W4306292690 cites W1885185971 @default.
• W4306292690 cites W1918250297 @default.
• W4306292690 cites W1978749115 @default.
• W4306292690 cites W1996726072 @default.
• W4306292690 cites W1999478721 @default.
• W4306292690 cites W2000323021 @default.
• W4306292690 cites W2001800591 @default.
• W4306292690 cites W2010070459 @default.
• W4306292690 cites W2038497950 @default.
• W4306292690 cites W2050849575 @default.
• W4306292690 cites W2058749767 @default.
• W4306292690 cites W2080744942 @default.
• W4306292690 cites W2088254198 @default.
• W4306292690 cites W2096683987 @default.
• W4306292690 cites W2099244020 @default.
• W4306292690 cites W2099712288 @default.
• W4306292690 cites W2100329651 @default.
• W4306292690 cites W2103106600 @default.
• W4306292690 cites W2104600947 @default.
• W4306292690 cites W2104620097 @default.
• W4306292690 cites W2104974755 @default.
• W4306292690 cites W2120824855 @default.
• W4306292690 cites W2121058967 @default.
• W4306292690 cites W2125188192 @default.
• W4306292690 cites W2131024476 @default.
• W4306292690 cites W2131349449 @default.
• W4306292690 cites W2133255058 @default.
• W4306292690 cites W2150081556 @default.
• W4306292690 cites W2153388956 @default.
• W4306292690 cites W2159203540 @default.
• W4306292690 cites W2164551808 @default.
• W4306292690 cites W2171211028 @default.
• W4306292690 cites W2214802144 @default.
• W4306292690 cites W2242218935 @default.
• W4306292690 cites W2291143146 @default.
• W4306292690 cites W2294512729 @default.
• W4306292690 cites W2345557152 @default.
• W4306292690 cites W2462592242 @default.
• W4306292690 cites W2503339013 @default.
• W4306292690 cites W2520322935 @default.
• W4306292690 cites W2520808298 @default.
• W4306292690 cites W2526558307 @default.
• W4306292690 cites W2709402577 @default.
• W4306292690 cites W2747898905 @default.
• W4306292690 cites W2777033955 @default.
• W4306292690 cites W2808495892 @default.
• W4306292690 cites W2866634454 @default.
• W4306292690 cites W2904488225 @default.
• W4306292690 cites W2963091558 @default.
• W4306292690 cites W2963183385 @default.
• W4306292690 cites W2963222130 @default.
• W4306292690 cites W2963870605 @default.
• W4306292690 cites W2963980268 @default.
• W4306292690 cites W2964007263 @default.
• W4306292690 cites W2964101377 @default.
• W4306292690 cites W2977745911 @default.
• W4306292690 cites W3014859219 @default.
• W4306292690 cites W3020887200 @default.
• W4306292690 cites W3035302306 @default.
• W4306292690 cites W3038079672 @default.
• W4306292690 cites W3049253011 @default.
• W4306292690 cites W3081397212 @default.
• W4306292690 cites W3100063120 @default.
• W4306292690 cites W3101690711 @default.
• W4306292690 cites W3102018640 @default.
• W4306292690 cites W3172472472 @default.
• W4306292690 cites W3181108287 @default.
• W4306292690 cites W3202223141 @default.
• W4306292690 cites W3204305289 @default.
• W4306292690 cites W3207407006 @default.
• W4306292690 cites W4206377169 @default.
• W4306292690 cites W4241716071 @default.
• W4306292690 cites W4283815286 @default.
• W4306292690 cites W4312918841 @default.
• W4306292690 cites W935139217 @default.
• W4306292690 doi "https://doi.org/10.1007/s11263-022-01699-1" @default.
• W4306292690 hasPublicationYear "2022" @default.
• W4306292690 type Work @default.
• W4306292690 citedByCount "9" @default.
• W4306292690 countsByYear W43062926902022 @default.
• W4306292690 countsByYear W43062926902023 @default.
• W4306292690 crossrefType "journal-article" @default.
• W4306292690 hasAuthorship W4306292690A5004164569 @default.
• W4306292690 hasAuthorship W4306292690A5020858452 @default.
• W4306292690 hasAuthorship W4306292690A5028103486 @default.
• W4306292690 hasAuthorship W4306292690A5057999649 @default.

• next