Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897096148> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2897096148 abstract "Lossy image compression usually introduces undesired compression artifacts, such as blocking, ringing and blurry effect{###} S, especially in low bit rate coding scenarios. Although many algorithms have been proposed to reduce these compression artifacts, most of them are based on image local smoothness prior, which usually leads to over-smoothing around the areas with distinct structures, e.g., edges and textures. In this paper, we propose a novel framework to enhance the perceptual quality of decoded images by well preserving the edge structures and predicting visually pleasing textures. Firstly, we propose an edge-preserving generative adversarial network (EP-GAN) to achieve edge restoration and texture generation simultaneously. Then, we elaborately design an edge fidelity regularization term to guide our network, which jointly utilizes the signal fidelity, feature fidelity and adversarial constraint to reconstruct high quality decoded images. Experimental results demonstrate that the proposed EP-GAN is able to efficiently enhance decoded images at low bit rate and reconstruct more perceptually pleasing images with abundant textures and sharp edges." @default.
- W2897096148 created "2018-10-26" @default.
- W2897096148 creator A5039832462 @default.
- W2897096148 creator A5042401810 @default.
- W2897096148 creator A5055937409 @default.
- W2897096148 creator A5083282081 @default.
- W2897096148 date "2018-07-01" @default.
- W2897096148 modified "2023-10-03" @default.
- W2897096148 title "Enhanced Image Decoding via Edge-Preserving Generative Adversarial Networks" @default.
- W2897096148 cites W1984077106 @default.
- W2897096148 cites W2017620942 @default.
- W2897096148 cites W2071804214 @default.
- W2897096148 cites W2121927366 @default.
- W2897096148 cites W2133665775 @default.
- W2897096148 cites W2135065661 @default.
- W2897096148 cites W2142683286 @default.
- W2897096148 cites W2194775991 @default.
- W2897096148 cites W2474073286 @default.
- W2897096148 cites W2556068545 @default.
- W2897096148 cites W2962687329 @default.
- W2897096148 doi "https://doi.org/10.1109/icme.2018.8486495" @default.
- W2897096148 hasPublicationYear "2018" @default.
- W2897096148 type Work @default.
- W2897096148 sameAs 2897096148 @default.
- W2897096148 citedByCount "11" @default.
- W2897096148 countsByYear W28970961482019 @default.
- W2897096148 countsByYear W28970961482020 @default.
- W2897096148 countsByYear W28970961482022 @default.
- W2897096148 countsByYear W28970961482023 @default.
- W2897096148 crossrefType "proceedings-article" @default.
- W2897096148 hasAuthorship W2897096148A5039832462 @default.
- W2897096148 hasAuthorship W2897096148A5042401810 @default.
- W2897096148 hasAuthorship W2897096148A5055937409 @default.
- W2897096148 hasAuthorship W2897096148A5083282081 @default.
- W2897096148 hasConcept C106430172 @default.
- W2897096148 hasConcept C11413529 @default.
- W2897096148 hasConcept C115961682 @default.
- W2897096148 hasConcept C13481523 @default.
- W2897096148 hasConcept C153180895 @default.
- W2897096148 hasConcept C154945302 @default.
- W2897096148 hasConcept C162307627 @default.
- W2897096148 hasConcept C165021410 @default.
- W2897096148 hasConcept C31972630 @default.
- W2897096148 hasConcept C3770464 @default.
- W2897096148 hasConcept C41008148 @default.
- W2897096148 hasConcept C57273362 @default.
- W2897096148 hasConcept C57654395 @default.
- W2897096148 hasConcept C9417928 @default.
- W2897096148 hasConceptScore W2897096148C106430172 @default.
- W2897096148 hasConceptScore W2897096148C11413529 @default.
- W2897096148 hasConceptScore W2897096148C115961682 @default.
- W2897096148 hasConceptScore W2897096148C13481523 @default.
- W2897096148 hasConceptScore W2897096148C153180895 @default.
- W2897096148 hasConceptScore W2897096148C154945302 @default.
- W2897096148 hasConceptScore W2897096148C162307627 @default.
- W2897096148 hasConceptScore W2897096148C165021410 @default.
- W2897096148 hasConceptScore W2897096148C31972630 @default.
- W2897096148 hasConceptScore W2897096148C3770464 @default.
- W2897096148 hasConceptScore W2897096148C41008148 @default.
- W2897096148 hasConceptScore W2897096148C57273362 @default.
- W2897096148 hasConceptScore W2897096148C57654395 @default.
- W2897096148 hasConceptScore W2897096148C9417928 @default.
- W2897096148 hasLocation W28970961481 @default.
- W2897096148 hasOpenAccess W2897096148 @default.
- W2897096148 hasPrimaryLocation W28970961481 @default.
- W2897096148 hasRelatedWork W2005185696 @default.
- W2897096148 hasRelatedWork W2048756857 @default.
- W2897096148 hasRelatedWork W2963001579 @default.
- W2897096148 hasRelatedWork W3017161950 @default.
- W2897096148 hasRelatedWork W3156291593 @default.
- W2897096148 hasRelatedWork W3165231707 @default.
- W2897096148 hasRelatedWork W3181034584 @default.
- W2897096148 hasRelatedWork W4206598283 @default.
- W2897096148 hasRelatedWork W4220812973 @default.
- W2897096148 hasRelatedWork W4283579220 @default.
- W2897096148 isParatext "false" @default.
- W2897096148 isRetracted "false" @default.
- W2897096148 magId "2897096148" @default.
- W2897096148 workType "article" @default.