Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328008201> ?p ?o ?g. }
- W4328008201 endingPage "5537" @default.
- W4328008201 startingPage "5525" @default.
- W4328008201 abstract "Image deblurring aims to restore the detailed texture information or structures from the blurry images, which has become an indispensable step in many computer vision tasks. Although various methods have been proposed to deal with the image deblurring problem, most of them treated the blurry image as a whole and neglected the characteristics of different image frequencies. In this paper, we present a new method called multi-scale frequency separation network (MSFS-Net) for image deblurring. MSFS-Net introduces the frequency separation module (FSM) into an encoder-decoder network architecture to capture the low- and high-frequency information of image at multiple scales. Then, a simple cycle-consistency strategy and a sophisticated contrastive learning module (CLM) are respectively designed to retain the low-frequency information and recover the high-frequency information during deblurring. At last, the features of different scales are fused by a cross-scale feature fusion module (CSFFM). Extensive experiments on benchmark datasets show that the proposed network achieves state-of-the-art performance." @default.
- W4328008201 created "2023-03-22" @default.
- W4328008201 creator A5005068793 @default.
- W4328008201 creator A5007680192 @default.
- W4328008201 creator A5048246275 @default.
- W4328008201 creator A5060042554 @default.
- W4328008201 creator A5069771802 @default.
- W4328008201 creator A5087038095 @default.
- W4328008201 date "2023-10-01" @default.
- W4328008201 modified "2023-10-10" @default.
- W4328008201 title "Multi-Scale Frequency Separation Network for Image Deblurring" @default.
- W4328008201 cites W1457323852 @default.
- W4328008201 cites W1916935112 @default.
- W4328008201 cites W2138621090 @default.
- W4328008201 cites W2300657047 @default.
- W4328008201 cites W2476548250 @default.
- W4328008201 cites W2509784253 @default.
- W4328008201 cites W2560533888 @default.
- W4328008201 cites W2562637781 @default.
- W4328008201 cites W2798735168 @default.
- W4328008201 cites W2953655861 @default.
- W4328008201 cites W2961218591 @default.
- W4328008201 cites W2963312584 @default.
- W4328008201 cites W2964030969 @default.
- W4328008201 cites W2965217508 @default.
- W4328008201 cites W2982795046 @default.
- W4328008201 cites W2988396473 @default.
- W4328008201 cites W2988641380 @default.
- W4328008201 cites W2997058852 @default.
- W4328008201 cites W3003954661 @default.
- W4328008201 cites W3011456574 @default.
- W4328008201 cites W3014483994 @default.
- W4328008201 cites W3023341321 @default.
- W4328008201 cites W3034347085 @default.
- W4328008201 cites W3034789174 @default.
- W4328008201 cites W3035212231 @default.
- W4328008201 cites W3035467803 @default.
- W4328008201 cites W3035484352 @default.
- W4328008201 cites W3085824656 @default.
- W4328008201 cites W3100506797 @default.
- W4328008201 cites W3107405705 @default.
- W4328008201 cites W3108316907 @default.
- W4328008201 cites W3109494165 @default.
- W4328008201 cites W3168684807 @default.
- W4328008201 cites W3168939832 @default.
- W4328008201 cites W3170697543 @default.
- W4328008201 cites W3173269149 @default.
- W4328008201 cites W3174154150 @default.
- W4328008201 cites W3174970555 @default.
- W4328008201 cites W3175200587 @default.
- W4328008201 cites W3175591478 @default.
- W4328008201 cites W3176096490 @default.
- W4328008201 cites W3177415989 @default.
- W4328008201 cites W3192778027 @default.
- W4328008201 cites W3202040256 @default.
- W4328008201 cites W3202362072 @default.
- W4328008201 cites W3207516177 @default.
- W4328008201 cites W4220843182 @default.
- W4328008201 cites W4221146732 @default.
- W4328008201 cites W4229862590 @default.
- W4328008201 cites W4292136513 @default.
- W4328008201 cites W4293370661 @default.
- W4328008201 cites W4303699847 @default.
- W4328008201 cites W4306809760 @default.
- W4328008201 cites W4308236198 @default.
- W4328008201 cites W4312432424 @default.
- W4328008201 cites W4312452088 @default.
- W4328008201 cites W4312756164 @default.
- W4328008201 cites W4312873952 @default.
- W4328008201 doi "https://doi.org/10.1109/tcsvt.2023.3259393" @default.
- W4328008201 hasPublicationYear "2023" @default.
- W4328008201 type Work @default.
- W4328008201 citedByCount "0" @default.
- W4328008201 crossrefType "journal-article" @default.
- W4328008201 hasAuthorship W4328008201A5005068793 @default.
- W4328008201 hasAuthorship W4328008201A5007680192 @default.
- W4328008201 hasAuthorship W4328008201A5048246275 @default.
- W4328008201 hasAuthorship W4328008201A5060042554 @default.
- W4328008201 hasAuthorship W4328008201A5069771802 @default.
- W4328008201 hasAuthorship W4328008201A5087038095 @default.
- W4328008201 hasBestOaLocation W43280082012 @default.
- W4328008201 hasConcept C106430172 @default.
- W4328008201 hasConcept C115961682 @default.
- W4328008201 hasConcept C13280743 @default.
- W4328008201 hasConcept C138885662 @default.
- W4328008201 hasConcept C153180895 @default.
- W4328008201 hasConcept C154945302 @default.
- W4328008201 hasConcept C185798385 @default.
- W4328008201 hasConcept C205649164 @default.
- W4328008201 hasConcept C2776401178 @default.
- W4328008201 hasConcept C2777693668 @default.
- W4328008201 hasConcept C31972630 @default.
- W4328008201 hasConcept C41008148 @default.
- W4328008201 hasConcept C41895202 @default.
- W4328008201 hasConcept C63099799 @default.
- W4328008201 hasConcept C9417928 @default.
- W4328008201 hasConceptScore W4328008201C106430172 @default.
- W4328008201 hasConceptScore W4328008201C115961682 @default.