Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386101152> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4386101152 endingPage "121131" @default.
- W4386101152 startingPage "121131" @default.
- W4386101152 abstract "Face beautification is an emerging application widely used in the entertainment industry. Previous studies have proved that Generative Adversarial Networks (GANs) can successfully build the mapping from a general face to a target face. However, their facial style code in the latent space is taken as a black box with a lack of semantics interpretation. They usually fail to consider the geometric semantic information (indicating the outline of the face and facial organs), and can not focus on the facial beauty-related regions. Moreover, most of them change the background information. To overcome these problems, we propose a novel Interpretable Semantic Generative Adversarial Network (ISFB-GAN) for face beautification. First, we design a new dual-branch facial style encoder to factorize the abundant semantic information of the reference face into the facial geometry style codes and the appearance style codes in the latent space. Then, a novelty facial attention generator is proposed to preserve the background information of the generated images. In the attention generator, the facial style attention is designed to focus on the most discriminative facial region; the background attention is designed to retain the background information. Finally, we propose a hybrid loss function including geometric loss, orthogonality loss, segmentation loss, style reconstruction loss, perceptual loss, etc., to enhance the learning capacity and improve the visual quality. The combination of the geometric loss and the orthogonality loss is deployed to guarantee the disentanglement between the semantic information. Extensive experiments conducted on the CelebAMask-HQ dataset and the SCUT-FBP5500 dataset, demonstrate that ISFB-GAN performs better than the state-of-the-art methods in facial attractiveness enhancement." @default.
- W4386101152 created "2023-08-24" @default.
- W4386101152 creator A5001633124 @default.
- W4386101152 creator A5004565086 @default.
- W4386101152 creator A5020626013 @default.
- W4386101152 creator A5026662451 @default.
- W4386101152 creator A5035282926 @default.
- W4386101152 creator A5067402912 @default.
- W4386101152 creator A5072611080 @default.
- W4386101152 date "2024-02-01" @default.
- W4386101152 modified "2023-09-26" @default.
- W4386101152 title "ISFB-GAN: Interpretable semantic face beautification with generative adversarial network" @default.
- W4386101152 cites W2003118627 @default.
- W4386101152 cites W2003168146 @default.
- W4386101152 cites W2743247818 @default.
- W4386101152 cites W2756182389 @default.
- W4386101152 cites W3092200346 @default.
- W4386101152 cites W3113141251 @default.
- W4386101152 cites W3165584357 @default.
- W4386101152 cites W4280558075 @default.
- W4386101152 cites W4319442358 @default.
- W4386101152 cites W4327846218 @default.
- W4386101152 doi "https://doi.org/10.1016/j.eswa.2023.121131" @default.
- W4386101152 hasPublicationYear "2024" @default.
- W4386101152 type Work @default.
- W4386101152 citedByCount "0" @default.
- W4386101152 crossrefType "journal-article" @default.
- W4386101152 hasAuthorship W4386101152A5001633124 @default.
- W4386101152 hasAuthorship W4386101152A5004565086 @default.
- W4386101152 hasAuthorship W4386101152A5020626013 @default.
- W4386101152 hasAuthorship W4386101152A5026662451 @default.
- W4386101152 hasAuthorship W4386101152A5035282926 @default.
- W4386101152 hasAuthorship W4386101152A5067402912 @default.
- W4386101152 hasAuthorship W4386101152A5072611080 @default.
- W4386101152 hasConcept C120665830 @default.
- W4386101152 hasConcept C121332964 @default.
- W4386101152 hasConcept C144024400 @default.
- W4386101152 hasConcept C154945302 @default.
- W4386101152 hasConcept C192209626 @default.
- W4386101152 hasConcept C2779304628 @default.
- W4386101152 hasConcept C36289849 @default.
- W4386101152 hasConcept C41008148 @default.
- W4386101152 hasConceptScore W4386101152C120665830 @default.
- W4386101152 hasConceptScore W4386101152C121332964 @default.
- W4386101152 hasConceptScore W4386101152C144024400 @default.
- W4386101152 hasConceptScore W4386101152C154945302 @default.
- W4386101152 hasConceptScore W4386101152C192209626 @default.
- W4386101152 hasConceptScore W4386101152C2779304628 @default.
- W4386101152 hasConceptScore W4386101152C36289849 @default.
- W4386101152 hasConceptScore W4386101152C41008148 @default.
- W4386101152 hasFunder F4320321001 @default.
- W4386101152 hasFunder F4320326705 @default.
- W4386101152 hasFunder F4320335952 @default.
- W4386101152 hasLocation W43861011521 @default.
- W4386101152 hasOpenAccess W4386101152 @default.
- W4386101152 hasPrimaryLocation W43861011521 @default.
- W4386101152 hasRelatedWork W1584420410 @default.
- W4386101152 hasRelatedWork W2015192756 @default.
- W4386101152 hasRelatedWork W2048360808 @default.
- W4386101152 hasRelatedWork W2057064510 @default.
- W4386101152 hasRelatedWork W2103413230 @default.
- W4386101152 hasRelatedWork W2120815133 @default.
- W4386101152 hasRelatedWork W2355490025 @default.
- W4386101152 hasRelatedWork W4249271267 @default.
- W4386101152 hasRelatedWork W4298145887 @default.
- W4386101152 hasRelatedWork W4323307419 @default.
- W4386101152 hasVolume "236" @default.
- W4386101152 isParatext "false" @default.
- W4386101152 isRetracted "false" @default.
- W4386101152 workType "article" @default.