Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990761323> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2990761323 abstract "The purpose of this paper is to present a context learning algorithm for inpainting missing regions using visual features. This encoder learns physical structure and semantic information from the image and this representation differentiates it from simple auto encoders. Such properties are crucial for tasks like image in-painting, classification and detection. Training was performed by patch-wise reconstruction loss using Structural Similarity (SSIM) jointly with an adversarial loss. The reconstruction loss is also augmented using spatially varying saliency maps that increase the error penalty on distinctive regions and thus promote image sharpness. Furthermore, in order to improve image continuity on the boundary of the missing region, distance functions with increasing importance towards the center of the inpainting region are also used either independently or in conjunction with the saliency maps. We also show that our choice of reconstruction loss outperforms conventional criteria such as the L2 norm. This means giving more weight to pixels closer to the border of the missing image parts and also giving more important to salience parts of the image to guide the reconstruction, thus producing more realistic images." @default.
- W2990761323 created "2019-12-05" @default.
- W2990761323 creator A5048652955 @default.
- W2990761323 creator A5075768628 @default.
- W2990761323 creator A5086544271 @default.
- W2990761323 date "2019-01-01" @default.
- W2990761323 modified "2023-09-25" @default.
- W2990761323 title "Hierarchical Image Inpainting by a Deep Context Encoder Exploiting Structural Similarity and Saliency Criteria" @default.
- W2990761323 cites W1699734612 @default.
- W2990761323 cites W1975049209 @default.
- W2990761323 cites W1993120651 @default.
- W2990761323 cites W1996819593 @default.
- W2990761323 cites W2076063813 @default.
- W2990761323 cites W2108598243 @default.
- W2990761323 cites W2115273023 @default.
- W2990761323 cites W2116013899 @default.
- W2990761323 cites W2129933262 @default.
- W2990761323 cites W2133665775 @default.
- W2990761323 cites W2150410007 @default.
- W2990761323 cites W2151690846 @default.
- W2990761323 cites W2412782625 @default.
- W2990761323 cites W2562637781 @default.
- W2990761323 cites W2962770929 @default.
- W2990761323 cites W2963420272 @default.
- W2990761323 doi "https://doi.org/10.1007/978-3-030-34995-0_42" @default.
- W2990761323 hasPublicationYear "2019" @default.
- W2990761323 type Work @default.
- W2990761323 sameAs 2990761323 @default.
- W2990761323 citedByCount "1" @default.
- W2990761323 countsByYear W29907613232020 @default.
- W2990761323 crossrefType "book-chapter" @default.
- W2990761323 hasAuthorship W2990761323A5048652955 @default.
- W2990761323 hasAuthorship W2990761323A5075768628 @default.
- W2990761323 hasAuthorship W2990761323A5086544271 @default.
- W2990761323 hasConcept C103278499 @default.
- W2990761323 hasConcept C108154423 @default.
- W2990761323 hasConcept C108583219 @default.
- W2990761323 hasConcept C111919701 @default.
- W2990761323 hasConcept C115961682 @default.
- W2990761323 hasConcept C11727466 @default.
- W2990761323 hasConcept C118505674 @default.
- W2990761323 hasConcept C141379421 @default.
- W2990761323 hasConcept C151730666 @default.
- W2990761323 hasConcept C153180895 @default.
- W2990761323 hasConcept C154945302 @default.
- W2990761323 hasConcept C160633673 @default.
- W2990761323 hasConcept C2779343474 @default.
- W2990761323 hasConcept C31972630 @default.
- W2990761323 hasConcept C41008148 @default.
- W2990761323 hasConcept C86803240 @default.
- W2990761323 hasConceptScore W2990761323C103278499 @default.
- W2990761323 hasConceptScore W2990761323C108154423 @default.
- W2990761323 hasConceptScore W2990761323C108583219 @default.
- W2990761323 hasConceptScore W2990761323C111919701 @default.
- W2990761323 hasConceptScore W2990761323C115961682 @default.
- W2990761323 hasConceptScore W2990761323C11727466 @default.
- W2990761323 hasConceptScore W2990761323C118505674 @default.
- W2990761323 hasConceptScore W2990761323C141379421 @default.
- W2990761323 hasConceptScore W2990761323C151730666 @default.
- W2990761323 hasConceptScore W2990761323C153180895 @default.
- W2990761323 hasConceptScore W2990761323C154945302 @default.
- W2990761323 hasConceptScore W2990761323C160633673 @default.
- W2990761323 hasConceptScore W2990761323C2779343474 @default.
- W2990761323 hasConceptScore W2990761323C31972630 @default.
- W2990761323 hasConceptScore W2990761323C41008148 @default.
- W2990761323 hasConceptScore W2990761323C86803240 @default.
- W2990761323 hasLocation W29907613231 @default.
- W2990761323 hasOpenAccess W2990761323 @default.
- W2990761323 hasPrimaryLocation W29907613231 @default.
- W2990761323 hasRelatedWork W1974878844 @default.
- W2990761323 hasRelatedWork W2005185696 @default.
- W2990761323 hasRelatedWork W2116330865 @default.
- W2990761323 hasRelatedWork W2126489883 @default.
- W2990761323 hasRelatedWork W2383395053 @default.
- W2990761323 hasRelatedWork W2767972054 @default.
- W2990761323 hasRelatedWork W2964148878 @default.
- W2990761323 hasRelatedWork W4210676101 @default.
- W2990761323 hasRelatedWork W2497752714 @default.
- W2990761323 hasRelatedWork W2551465695 @default.
- W2990761323 isParatext "false" @default.
- W2990761323 isRetracted "false" @default.
- W2990761323 magId "2990761323" @default.
- W2990761323 workType "book-chapter" @default.