Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385801152> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4385801152 abstract "Blind face restoration aims to recover high-quality face images from unknown degraded low-quality images. Previous works that are based on geometric or generative priors have achieved impressive performance, but the task remains challenging, particularly when it comes to restoring severely degraded faces. To address this issue, we propose a novel approach TFRGAN, that leverages textual information to improve the restoration of extremely degraded face images. Specifically, we propose to generate a better and more accurate latent code for StyleGAN2 prior via fusing the text and image information in the latent code space. Besides, extracted textual features are used to modulate the decoding features to obtain more realistic and natural facial images with more reasonable details. Experimental results demonstrate the superiority of the proposed method for restoring severely degraded face images." @default.
- W4385801152 created "2023-08-15" @default.
- W4385801152 creator A5022200044 @default.
- W4385801152 creator A5037310802 @default.
- W4385801152 creator A5042112278 @default.
- W4385801152 creator A5077166272 @default.
- W4385801152 date "2023-06-01" @default.
- W4385801152 modified "2023-10-16" @default.
- W4385801152 title "TFRGAN: Leveraging Text Information for Blind Face Restoration with Extreme Degradation" @default.
- W4385801152 cites W2102166818 @default.
- W4385801152 cites W2133665775 @default.
- W4385801152 cites W2895542678 @default.
- W4385801152 cites W2962770929 @default.
- W4385801152 cites W2962785568 @default.
- W4385801152 cites W2963312584 @default.
- W4385801152 cites W2963393566 @default.
- W4385801152 cites W2963676087 @default.
- W4385801152 cites W2963743395 @default.
- W4385801152 cites W2963814095 @default.
- W4385801152 cites W2964337551 @default.
- W4385801152 cites W3021195052 @default.
- W4385801152 cites W3034352949 @default.
- W4385801152 cites W3034521057 @default.
- W4385801152 cites W3096831136 @default.
- W4385801152 cites W3167297682 @default.
- W4385801152 cites W3174166237 @default.
- W4385801152 cites W3174194560 @default.
- W4385801152 cites W3180355996 @default.
- W4385801152 cites W3180391059 @default.
- W4385801152 cites W3203631022 @default.
- W4385801152 cites W3208722310 @default.
- W4385801152 cites W4242059867 @default.
- W4385801152 cites W4312326192 @default.
- W4385801152 doi "https://doi.org/10.1109/cvprw59228.2023.00252" @default.
- W4385801152 hasPublicationYear "2023" @default.
- W4385801152 type Work @default.
- W4385801152 citedByCount "0" @default.
- W4385801152 crossrefType "proceedings-article" @default.
- W4385801152 hasAuthorship W4385801152A5022200044 @default.
- W4385801152 hasAuthorship W4385801152A5037310802 @default.
- W4385801152 hasAuthorship W4385801152A5042112278 @default.
- W4385801152 hasAuthorship W4385801152A5077166272 @default.
- W4385801152 hasConcept C106430172 @default.
- W4385801152 hasConcept C11413529 @default.
- W4385801152 hasConcept C115961682 @default.
- W4385801152 hasConcept C144024400 @default.
- W4385801152 hasConcept C153180895 @default.
- W4385801152 hasConcept C154945302 @default.
- W4385801152 hasConcept C167966045 @default.
- W4385801152 hasConcept C177264268 @default.
- W4385801152 hasConcept C199360897 @default.
- W4385801152 hasConcept C2776760102 @default.
- W4385801152 hasConcept C2779304628 @default.
- W4385801152 hasConcept C31510193 @default.
- W4385801152 hasConcept C31972630 @default.
- W4385801152 hasConcept C36289849 @default.
- W4385801152 hasConcept C39890363 @default.
- W4385801152 hasConcept C41008148 @default.
- W4385801152 hasConcept C57273362 @default.
- W4385801152 hasConcept C9417928 @default.
- W4385801152 hasConceptScore W4385801152C106430172 @default.
- W4385801152 hasConceptScore W4385801152C11413529 @default.
- W4385801152 hasConceptScore W4385801152C115961682 @default.
- W4385801152 hasConceptScore W4385801152C144024400 @default.
- W4385801152 hasConceptScore W4385801152C153180895 @default.
- W4385801152 hasConceptScore W4385801152C154945302 @default.
- W4385801152 hasConceptScore W4385801152C167966045 @default.
- W4385801152 hasConceptScore W4385801152C177264268 @default.
- W4385801152 hasConceptScore W4385801152C199360897 @default.
- W4385801152 hasConceptScore W4385801152C2776760102 @default.
- W4385801152 hasConceptScore W4385801152C2779304628 @default.
- W4385801152 hasConceptScore W4385801152C31510193 @default.
- W4385801152 hasConceptScore W4385801152C31972630 @default.
- W4385801152 hasConceptScore W4385801152C36289849 @default.
- W4385801152 hasConceptScore W4385801152C39890363 @default.
- W4385801152 hasConceptScore W4385801152C41008148 @default.
- W4385801152 hasConceptScore W4385801152C57273362 @default.
- W4385801152 hasConceptScore W4385801152C9417928 @default.
- W4385801152 hasLocation W43858011521 @default.
- W4385801152 hasOpenAccess W4385801152 @default.
- W4385801152 hasPrimaryLocation W43858011521 @default.
- W4385801152 hasRelatedWork W1598401975 @default.
- W4385801152 hasRelatedWork W1775397219 @default.
- W4385801152 hasRelatedWork W2103413230 @default.
- W4385801152 hasRelatedWork W2130228941 @default.
- W4385801152 hasRelatedWork W2347601237 @default.
- W4385801152 hasRelatedWork W2885442750 @default.
- W4385801152 hasRelatedWork W2897995864 @default.
- W4385801152 hasRelatedWork W2908959303 @default.
- W4385801152 hasRelatedWork W3161240412 @default.
- W4385801152 hasRelatedWork W4295275339 @default.
- W4385801152 isParatext "false" @default.
- W4385801152 isRetracted "false" @default.
- W4385801152 workType "article" @default.