Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140471502> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3140471502 abstract "Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to the difficulty in learning misaligned optical zoom. In this paper, we introduce a Squared Deformable Alignment Network (SDAN) to address this issue. Our network learns squared per-point offsets for convolutional kernels, and then aligns features in corrected convolutional windows based on the offsets. So the misalignment will be minimized by the extracted aligned features. Different from the per-point offsets used in the vanilla Deformable Convolutional Network (DCN), our proposed squared offsets not only accelerate the offset learning but also improve the generation quality with fewer parameters. Besides, we further propose an efficient cross packing attention layer to boost the accuracy of the learned offsets. It leverages the packing and unpacking operations to enlarge the receptive field of the offset learning and to enhance the ability of extracting the spatial connection between the low-resolution images and the referenced images. Comprehensive experiments show the superiority of our method over other state-of-the-art methods in both computational efficiency and realistic details." @default.
- W3140471502 created "2021-04-13" @default.
- W3140471502 creator A5029499523 @default.
- W3140471502 creator A5061336891 @default.
- W3140471502 creator A5068345931 @default.
- W3140471502 date "2021-04-01" @default.
- W3140471502 modified "2023-09-26" @default.
- W3140471502 title "SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom" @default.
- W3140471502 cites W1885185971 @default.
- W3140471502 cites W2331128040 @default.
- W3140471502 cites W2601564443 @default.
- W3140471502 cites W2891158090 @default.
- W3140471502 cites W2895598217 @default.
- W3140471502 cites W2943960148 @default.
- W3140471502 cites W2962785568 @default.
- W3140471502 cites W2962927175 @default.
- W3140471502 cites W2963372104 @default.
- W3140471502 cites W2963470893 @default.
- W3140471502 cites W2964040059 @default.
- W3140471502 cites W2965669158 @default.
- W3140471502 cites W2966926453 @default.
- W3140471502 cites W2986833982 @default.
- W3140471502 cites W3012166502 @default.
- W3140471502 cites W3034475761 @default.
- W3140471502 cites W3035047434 @default.
- W3140471502 cites W3095671795 @default.
- W3140471502 cites W3176675486 @default.
- W3140471502 doi "https://doi.org/10.48550/arxiv.2104.00848" @default.
- W3140471502 hasPublicationYear "2021" @default.
- W3140471502 type Work @default.
- W3140471502 sameAs 3140471502 @default.
- W3140471502 citedByCount "0" @default.
- W3140471502 crossrefType "posted-content" @default.
- W3140471502 hasAuthorship W3140471502A5029499523 @default.
- W3140471502 hasAuthorship W3140471502A5061336891 @default.
- W3140471502 hasAuthorship W3140471502A5068345931 @default.
- W3140471502 hasBestOaLocation W31404715021 @default.
- W3140471502 hasConcept C105795698 @default.
- W3140471502 hasConcept C108583219 @default.
- W3140471502 hasConcept C11413529 @default.
- W3140471502 hasConcept C115961682 @default.
- W3140471502 hasConcept C124913957 @default.
- W3140471502 hasConcept C127413603 @default.
- W3140471502 hasConcept C139945424 @default.
- W3140471502 hasConcept C141239990 @default.
- W3140471502 hasConcept C153180895 @default.
- W3140471502 hasConcept C15336307 @default.
- W3140471502 hasConcept C154945302 @default.
- W3140471502 hasConcept C175291020 @default.
- W3140471502 hasConcept C199360897 @default.
- W3140471502 hasConcept C31972630 @default.
- W3140471502 hasConcept C33923547 @default.
- W3140471502 hasConcept C41008148 @default.
- W3140471502 hasConcept C78762247 @default.
- W3140471502 hasConcept C81363708 @default.
- W3140471502 hasConceptScore W3140471502C105795698 @default.
- W3140471502 hasConceptScore W3140471502C108583219 @default.
- W3140471502 hasConceptScore W3140471502C11413529 @default.
- W3140471502 hasConceptScore W3140471502C115961682 @default.
- W3140471502 hasConceptScore W3140471502C124913957 @default.
- W3140471502 hasConceptScore W3140471502C127413603 @default.
- W3140471502 hasConceptScore W3140471502C139945424 @default.
- W3140471502 hasConceptScore W3140471502C141239990 @default.
- W3140471502 hasConceptScore W3140471502C153180895 @default.
- W3140471502 hasConceptScore W3140471502C15336307 @default.
- W3140471502 hasConceptScore W3140471502C154945302 @default.
- W3140471502 hasConceptScore W3140471502C175291020 @default.
- W3140471502 hasConceptScore W3140471502C199360897 @default.
- W3140471502 hasConceptScore W3140471502C31972630 @default.
- W3140471502 hasConceptScore W3140471502C33923547 @default.
- W3140471502 hasConceptScore W3140471502C41008148 @default.
- W3140471502 hasConceptScore W3140471502C78762247 @default.
- W3140471502 hasConceptScore W3140471502C81363708 @default.
- W3140471502 hasLocation W31404715021 @default.
- W3140471502 hasLocation W31404715022 @default.
- W3140471502 hasOpenAccess W3140471502 @default.
- W3140471502 hasPrimaryLocation W31404715021 @default.
- W3140471502 hasRelatedWork W2731899572 @default.
- W3140471502 hasRelatedWork W2738221750 @default.
- W3140471502 hasRelatedWork W2921281359 @default.
- W3140471502 hasRelatedWork W3133861977 @default.
- W3140471502 hasRelatedWork W3156786002 @default.
- W3140471502 hasRelatedWork W4200173597 @default.
- W3140471502 hasRelatedWork W4200550458 @default.
- W3140471502 hasRelatedWork W4312417841 @default.
- W3140471502 hasRelatedWork W4321369474 @default.
- W3140471502 hasRelatedWork W564581980 @default.
- W3140471502 isParatext "false" @default.
- W3140471502 isRetracted "false" @default.
- W3140471502 magId "3140471502" @default.
- W3140471502 workType "article" @default.