Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035251567> ?p ?o ?g. }
- W3035251567 endingPage "1322" @default.
- W3035251567 startingPage "1308" @default.
- W3035251567 abstract "Deep learning-based methods especially using convolutional neural network (CNN) and generative adversarial network (GAN) have achieved certain success for the task of image inpainting. The previous methods usually try to generate the content in the missing areas from scratch. However, these methods have difficulty in producing salient image structures that appear natural and consistent with the neighborhood, especially when the missing area is large. In this paper, we address the challenge by introducing edges into the convolutional GAN-based inpainting. We split the inpainting task into two steps: first edge generation, then edge-based image generation. We adopt CNN to accomplish the two steps and use GAN-based training, thus our method is named E2I: generative inpainting from edge to image. Specifically, we adopt a deep network-based edge detector to achieve an edgeness map of an incomplete image, then we fill-in the missing areas in the edgeness map, and finally generate the missing pixels with the assistance of the complete edgeness map. We verify the proposed method on three challenging image datasets: Places2, ImageNet, and CelebA. We also compare our method with the state-of-the-arts on the Places2 test set. Our experimental results demonstrate the superior performance of our method in producing more plausible inpainting results." @default.
- W3035251567 created "2020-06-19" @default.
- W3035251567 creator A5008612863 @default.
- W3035251567 creator A5017490817 @default.
- W3035251567 creator A5036359599 @default.
- W3035251567 date "2021-04-01" @default.
- W3035251567 modified "2023-10-15" @default.
- W3035251567 title "E2I: Generative Inpainting From Edge to Image" @default.
- W3035251567 cites W1560055586 @default.
- W3035251567 cites W1834627138 @default.
- W3035251567 cites W1993120651 @default.
- W3035251567 cites W2012875423 @default.
- W3035251567 cites W2064309976 @default.
- W3035251567 cites W2105038642 @default.
- W3035251567 cites W2108598243 @default.
- W3035251567 cites W2110158442 @default.
- W3035251567 cites W2116013899 @default.
- W3035251567 cites W2130639964 @default.
- W3035251567 cites W2138715174 @default.
- W3035251567 cites W2145023731 @default.
- W3035251567 cites W2147901574 @default.
- W3035251567 cites W2158315003 @default.
- W3035251567 cites W2161952492 @default.
- W3035251567 cites W2162449045 @default.
- W3035251567 cites W2295936755 @default.
- W3035251567 cites W2344939607 @default.
- W3035251567 cites W2517325737 @default.
- W3035251567 cites W2557414982 @default.
- W3035251567 cites W2732026016 @default.
- W3035251567 cites W2738588019 @default.
- W3035251567 cites W2791679901 @default.
- W3035251567 cites W2796286534 @default.
- W3035251567 cites W2799277064 @default.
- W3035251567 cites W2900538548 @default.
- W3035251567 cites W2948500402 @default.
- W3035251567 cites W2962872526 @default.
- W3035251567 cites W2963073614 @default.
- W3035251567 cites W2963270367 @default.
- W3035251567 cites W2963420272 @default.
- W3035251567 cites W2963659230 @default.
- W3035251567 cites W2963660453 @default.
- W3035251567 cites W2963917315 @default.
- W3035251567 cites W2990984982 @default.
- W3035251567 cites W2991377405 @default.
- W3035251567 cites W3001217199 @default.
- W3035251567 cites W3043547428 @default.
- W3035251567 cites W4240726888 @default.
- W3035251567 cites W845365781 @default.
- W3035251567 doi "https://doi.org/10.1109/tcsvt.2020.3001267" @default.
- W3035251567 hasPublicationYear "2021" @default.
- W3035251567 type Work @default.
- W3035251567 sameAs 3035251567 @default.
- W3035251567 citedByCount "33" @default.
- W3035251567 countsByYear W30352515672021 @default.
- W3035251567 countsByYear W30352515672022 @default.
- W3035251567 countsByYear W30352515672023 @default.
- W3035251567 crossrefType "journal-article" @default.
- W3035251567 hasAuthorship W3035251567A5008612863 @default.
- W3035251567 hasAuthorship W3035251567A5017490817 @default.
- W3035251567 hasAuthorship W3035251567A5036359599 @default.
- W3035251567 hasConcept C108583219 @default.
- W3035251567 hasConcept C115961682 @default.
- W3035251567 hasConcept C11727466 @default.
- W3035251567 hasConcept C153180895 @default.
- W3035251567 hasConcept C154945302 @default.
- W3035251567 hasConcept C160633673 @default.
- W3035251567 hasConcept C162307627 @default.
- W3035251567 hasConcept C200873422 @default.
- W3035251567 hasConcept C31972630 @default.
- W3035251567 hasConcept C41008148 @default.
- W3035251567 hasConcept C45347329 @default.
- W3035251567 hasConcept C50644808 @default.
- W3035251567 hasConcept C81363708 @default.
- W3035251567 hasConceptScore W3035251567C108583219 @default.
- W3035251567 hasConceptScore W3035251567C115961682 @default.
- W3035251567 hasConceptScore W3035251567C11727466 @default.
- W3035251567 hasConceptScore W3035251567C153180895 @default.
- W3035251567 hasConceptScore W3035251567C154945302 @default.
- W3035251567 hasConceptScore W3035251567C160633673 @default.
- W3035251567 hasConceptScore W3035251567C162307627 @default.
- W3035251567 hasConceptScore W3035251567C200873422 @default.
- W3035251567 hasConceptScore W3035251567C31972630 @default.
- W3035251567 hasConceptScore W3035251567C41008148 @default.
- W3035251567 hasConceptScore W3035251567C45347329 @default.
- W3035251567 hasConceptScore W3035251567C50644808 @default.
- W3035251567 hasConceptScore W3035251567C81363708 @default.
- W3035251567 hasFunder F4320321001 @default.
- W3035251567 hasFunder F4320335777 @default.
- W3035251567 hasIssue "4" @default.
- W3035251567 hasLocation W30352515671 @default.
- W3035251567 hasOpenAccess W3035251567 @default.
- W3035251567 hasPrimaryLocation W30352515671 @default.
- W3035251567 hasRelatedWork W1533292911 @default.
- W3035251567 hasRelatedWork W2121879286 @default.
- W3035251567 hasRelatedWork W2385194032 @default.
- W3035251567 hasRelatedWork W2414884753 @default.
- W3035251567 hasRelatedWork W2606416966 @default.
- W3035251567 hasRelatedWork W2780405157 @default.