Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205803261> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3205803261 abstract "Old photos are an important carrier to preserve the past. Usually, the degradation of old photos is rather diverse and complex. Therefore, the existing methods to solve conventional restoration tasks are difficult to generalize. To solve this problem, we propose a novel method based on generative adversarial network. Our method utilizes the class-attributes of old photos to complete restoration in latent space. Specifically, we divide the process of restoring old photos into two stages, one is global defect restoration stage and the other is local detail restoration stage. In global defect restoration stage, we extract the latent representations of four classes of high-level attributes that are smoothness, clarity, connectivity and completeness. We use latent class-attribute information to restore global defects in latent space and we obtain conditional control vector through a condition network to guide the subsequent local detail restoration stage. In local detail restoration stage, we propose a dynamic condition-guided restoration module that selects the most suitable combination of features to further restore local details through a dynamic network. In addition, we propose a dual discriminator to pay more attention to style and defect restoration. We ignore the complex degradation of old photos to directly restore advanced class-attributes. Therefore, our method has better generalization performance. Experiments show that our method is superior to other existing methods of image restoration in terms of visual quality and numerical metrics." @default.
- W3205803261 created "2021-10-25" @default.
- W3205803261 creator A5010803633 @default.
- W3205803261 creator A5033420215 @default.
- W3205803261 creator A5053453125 @default.
- W3205803261 creator A5081669641 @default.
- W3205803261 date "2021-10-17" @default.
- W3205803261 modified "2023-10-13" @default.
- W3205803261 title "CG-GAN" @default.
- W3205803261 cites W2077903051 @default.
- W3205803261 cites W2097073572 @default.
- W3205803261 cites W2097713019 @default.
- W3205803261 cites W2536599074 @default.
- W3205803261 cites W2798365772 @default.
- W3205803261 cites W2963470893 @default.
- W3205803261 cites W2964297221 @default.
- W3205803261 cites W2964343197 @default.
- W3205803261 cites W3034785019 @default.
- W3205803261 cites W3035002246 @default.
- W3205803261 cites W3035558814 @default.
- W3205803261 cites W3035559491 @default.
- W3205803261 cites W3102061158 @default.
- W3205803261 cites W3143835446 @default.
- W3205803261 cites W4249710618 @default.
- W3205803261 doi "https://doi.org/10.1145/3474085.3475666" @default.
- W3205803261 hasPublicationYear "2021" @default.
- W3205803261 type Work @default.
- W3205803261 sameAs 3205803261 @default.
- W3205803261 citedByCount "5" @default.
- W3205803261 countsByYear W32058032612022 @default.
- W3205803261 countsByYear W32058032612023 @default.
- W3205803261 crossrefType "proceedings-article" @default.
- W3205803261 hasAuthorship W3205803261A5010803633 @default.
- W3205803261 hasAuthorship W3205803261A5033420215 @default.
- W3205803261 hasAuthorship W3205803261A5053453125 @default.
- W3205803261 hasAuthorship W3205803261A5081669641 @default.
- W3205803261 hasConcept C106430172 @default.
- W3205803261 hasConcept C115961682 @default.
- W3205803261 hasConcept C134306372 @default.
- W3205803261 hasConcept C153180895 @default.
- W3205803261 hasConcept C154945302 @default.
- W3205803261 hasConcept C17231256 @default.
- W3205803261 hasConcept C177148314 @default.
- W3205803261 hasConcept C2777212361 @default.
- W3205803261 hasConcept C2779803651 @default.
- W3205803261 hasConcept C33923547 @default.
- W3205803261 hasConcept C41008148 @default.
- W3205803261 hasConcept C76155785 @default.
- W3205803261 hasConcept C9417928 @default.
- W3205803261 hasConcept C94915269 @default.
- W3205803261 hasConceptScore W3205803261C106430172 @default.
- W3205803261 hasConceptScore W3205803261C115961682 @default.
- W3205803261 hasConceptScore W3205803261C134306372 @default.
- W3205803261 hasConceptScore W3205803261C153180895 @default.
- W3205803261 hasConceptScore W3205803261C154945302 @default.
- W3205803261 hasConceptScore W3205803261C17231256 @default.
- W3205803261 hasConceptScore W3205803261C177148314 @default.
- W3205803261 hasConceptScore W3205803261C2777212361 @default.
- W3205803261 hasConceptScore W3205803261C2779803651 @default.
- W3205803261 hasConceptScore W3205803261C33923547 @default.
- W3205803261 hasConceptScore W3205803261C41008148 @default.
- W3205803261 hasConceptScore W3205803261C76155785 @default.
- W3205803261 hasConceptScore W3205803261C9417928 @default.
- W3205803261 hasConceptScore W3205803261C94915269 @default.
- W3205803261 hasLocation W32058032611 @default.
- W3205803261 hasOpenAccess W3205803261 @default.
- W3205803261 hasPrimaryLocation W32058032611 @default.
- W3205803261 hasRelatedWork W2033914206 @default.
- W3205803261 hasRelatedWork W2091274708 @default.
- W3205803261 hasRelatedWork W2146076056 @default.
- W3205803261 hasRelatedWork W2163831990 @default.
- W3205803261 hasRelatedWork W2885094885 @default.
- W3205803261 hasRelatedWork W2906643110 @default.
- W3205803261 hasRelatedWork W2951337574 @default.
- W3205803261 hasRelatedWork W2975513049 @default.
- W3205803261 hasRelatedWork W4280544492 @default.
- W3205803261 hasRelatedWork W4312963184 @default.
- W3205803261 isParatext "false" @default.
- W3205803261 isRetracted "false" @default.
- W3205803261 magId "3205803261" @default.
- W3205803261 workType "article" @default.