Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312095843> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4312095843 abstract "In this paper, we propose an edge-guided video super-resolution (EGVSR) network that utilizes the edge information of the image to effectively recover high-frequency details for high-resolution frames. The reconstruction process consists of two stages. In the first stage, the Coarse Frame Reconstruction Network (CFRN) generates coarse SR frames. In addition, we propose the Edge-Prediction Network (EPN) to capture the edge details that help to supplement the missing high-frequency information. Unlike some prior SR works that tend to increase the depth of networks or use attention mechanisms to reconstruct large-size objects but ignore small-size objects, we propose the Attention Fusion Residual Block (AFRB) to process objects of different sizes. The AFRB, an enhanced version of the conventional residual block, performs fusion through a multi-scale channel attention mechanism and serves as the basic operation unit in the CFRN and the EPN. Then, in the second stage, we propose the Frame Refinement Network (FRN), which contains multiple convolution layers. Through the FRN, we fuse and refine the coarse SR frames and edge information learned from the first stage. Compared with the state-of-the-art methods, our SR model improves approximately 0.5% in PSNR and 1.8% in SSIM evaluation on the benchmark VID4 dataset when the number of parameters is reduced by 54%." @default.
- W4312095843 created "2023-01-04" @default.
- W4312095843 creator A5002012107 @default.
- W4312095843 creator A5019389546 @default.
- W4312095843 creator A5021224407 @default.
- W4312095843 creator A5028965356 @default.
- W4312095843 date "2022-11-07" @default.
- W4312095843 modified "2023-09-27" @default.
- W4312095843 title "Edge-Guided Video Super-Resolution Network" @default.
- W4312095843 cites W1981990039 @default.
- W4312095843 cites W2087401054 @default.
- W4312095843 cites W2121058967 @default.
- W4312095843 cites W2133665775 @default.
- W4312095843 cites W2781335552 @default.
- W4312095843 cites W2798664922 @default.
- W4312095843 cites W2904835235 @default.
- W4312095843 cites W2923834406 @default.
- W4312095843 cites W2986833982 @default.
- W4312095843 cites W3006138597 @default.
- W4312095843 cites W3010638262 @default.
- W4312095843 cites W3088779065 @default.
- W4312095843 cites W3094897602 @default.
- W4312095843 cites W3104196124 @default.
- W4312095843 cites W3105627233 @default.
- W4312095843 cites W3123507393 @default.
- W4312095843 cites W3128176988 @default.
- W4312095843 cites W3131720768 @default.
- W4312095843 cites W54257720 @default.
- W4312095843 doi "https://doi.org/10.1109/rasse54974.2022.9989570" @default.
- W4312095843 hasPublicationYear "2022" @default.
- W4312095843 type Work @default.
- W4312095843 citedByCount "0" @default.
- W4312095843 crossrefType "proceedings-article" @default.
- W4312095843 hasAuthorship W4312095843A5002012107 @default.
- W4312095843 hasAuthorship W4312095843A5019389546 @default.
- W4312095843 hasAuthorship W4312095843A5021224407 @default.
- W4312095843 hasAuthorship W4312095843A5028965356 @default.
- W4312095843 hasConcept C111919701 @default.
- W4312095843 hasConcept C11413529 @default.
- W4312095843 hasConcept C119599485 @default.
- W4312095843 hasConcept C126042441 @default.
- W4312095843 hasConcept C127413603 @default.
- W4312095843 hasConcept C13280743 @default.
- W4312095843 hasConcept C141353440 @default.
- W4312095843 hasConcept C141379421 @default.
- W4312095843 hasConcept C153180895 @default.
- W4312095843 hasConcept C154945302 @default.
- W4312095843 hasConcept C155512373 @default.
- W4312095843 hasConcept C162307627 @default.
- W4312095843 hasConcept C185798385 @default.
- W4312095843 hasConcept C205649164 @default.
- W4312095843 hasConcept C2524010 @default.
- W4312095843 hasConcept C2777210771 @default.
- W4312095843 hasConcept C31972630 @default.
- W4312095843 hasConcept C33923547 @default.
- W4312095843 hasConcept C41008148 @default.
- W4312095843 hasConcept C45347329 @default.
- W4312095843 hasConcept C50644808 @default.
- W4312095843 hasConcept C76155785 @default.
- W4312095843 hasConcept C98045186 @default.
- W4312095843 hasConceptScore W4312095843C111919701 @default.
- W4312095843 hasConceptScore W4312095843C11413529 @default.
- W4312095843 hasConceptScore W4312095843C119599485 @default.
- W4312095843 hasConceptScore W4312095843C126042441 @default.
- W4312095843 hasConceptScore W4312095843C127413603 @default.
- W4312095843 hasConceptScore W4312095843C13280743 @default.
- W4312095843 hasConceptScore W4312095843C141353440 @default.
- W4312095843 hasConceptScore W4312095843C141379421 @default.
- W4312095843 hasConceptScore W4312095843C153180895 @default.
- W4312095843 hasConceptScore W4312095843C154945302 @default.
- W4312095843 hasConceptScore W4312095843C155512373 @default.
- W4312095843 hasConceptScore W4312095843C162307627 @default.
- W4312095843 hasConceptScore W4312095843C185798385 @default.
- W4312095843 hasConceptScore W4312095843C205649164 @default.
- W4312095843 hasConceptScore W4312095843C2524010 @default.
- W4312095843 hasConceptScore W4312095843C2777210771 @default.
- W4312095843 hasConceptScore W4312095843C31972630 @default.
- W4312095843 hasConceptScore W4312095843C33923547 @default.
- W4312095843 hasConceptScore W4312095843C41008148 @default.
- W4312095843 hasConceptScore W4312095843C45347329 @default.
- W4312095843 hasConceptScore W4312095843C50644808 @default.
- W4312095843 hasConceptScore W4312095843C76155785 @default.
- W4312095843 hasConceptScore W4312095843C98045186 @default.
- W4312095843 hasFunder F4320309618 @default.
- W4312095843 hasLocation W43120958431 @default.
- W4312095843 hasOpenAccess W4312095843 @default.
- W4312095843 hasPrimaryLocation W43120958431 @default.
- W4312095843 hasRelatedWork W1988829224 @default.
- W4312095843 hasRelatedWork W2169891923 @default.
- W4312095843 hasRelatedWork W2330874859 @default.
- W4312095843 hasRelatedWork W2347743143 @default.
- W4312095843 hasRelatedWork W251639349 @default.
- W4312095843 hasRelatedWork W2912737833 @default.
- W4312095843 hasRelatedWork W3016486109 @default.
- W4312095843 hasRelatedWork W4206597275 @default.
- W4312095843 hasRelatedWork W4250616939 @default.
- W4312095843 hasRelatedWork W4315882045 @default.
- W4312095843 isParatext "false" @default.
- W4312095843 isRetracted "false" @default.
- W4312095843 workType "article" @default.