Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903157059> ?p ?o ?g. }
- W2903157059 abstract "Deep neural networks have recently been used to edit images with great success, in particular for faces. However, they are often limited to only being able to work at a restricted range of resolutions. Many methods are so flexible that face edits can often result in an unwanted loss of identity. This work proposes to learn how to perform semantic image edits through the application of smooth warp fields. Previous approaches that attempted to use warping for semantic edits required paired data, i.e. example images of the same subject with different semantic attributes. In contrast, we employ recent advances in Generative Adversarial Networks that allow our model to be trained with unpaired data. We demonstrate face editing at very high resolutions (4k images) with a single forward pass of a deep network at a lower resolution. We also show that our edits are substantially better at preserving the subject's identity. The robustness of our approach is demonstrated by showing plausible image editing results on the Cub200 birds dataset. To our knowledge this has not been previously accomplished, due the challenging nature of the dataset." @default.
- W2903157059 created "2018-12-11" @default.
- W2903157059 creator A5016753399 @default.
- W2903157059 creator A5040500007 @default.
- W2903157059 creator A5062576796 @default.
- W2903157059 creator A5087679173 @default.
- W2903157059 date "2018-11-30" @default.
- W2903157059 modified "2023-09-27" @default.
- W2903157059 title "The GAN that Warped: Semantic Attribute Editing with Unpaired Data" @default.
- W2903157059 cites W1578985305 @default.
- W2903157059 cites W1797268635 @default.
- W2903157059 cites W1834627138 @default.
- W2903157059 cites W1969306251 @default.
- W2903157059 cites W2020230579 @default.
- W2903157059 cites W2098693229 @default.
- W2903157059 cites W2099471712 @default.
- W2903157059 cites W2115252128 @default.
- W2903157059 cites W2301937176 @default.
- W2903157059 cites W2348664362 @default.
- W2903157059 cites W2508756538 @default.
- W2903157059 cites W2515770085 @default.
- W2903157059 cites W2519536754 @default.
- W2903157059 cites W2551717155 @default.
- W2903157059 cites W2558578635 @default.
- W2903157059 cites W2579578355 @default.
- W2903157059 cites W2739748921 @default.
- W2903157059 cites W2798841107 @default.
- W2903157059 cites W2807033398 @default.
- W2903157059 cites W2883861033 @default.
- W2903157059 cites W2893749619 @default.
- W2903157059 cites W2898275197 @default.
- W2903157059 cites W2902266071 @default.
- W2903157059 cites W2962760235 @default.
- W2903157059 cites W2962879692 @default.
- W2903157059 cites W2962927829 @default.
- W2903157059 cites W2963073614 @default.
- W2903157059 cites W2963420272 @default.
- W2903157059 cites W2963470893 @default.
- W2903157059 cites W2963684405 @default.
- W2903157059 cites W2963767194 @default.
- W2903157059 cites W2963870144 @default.
- W2903157059 cites W2964082390 @default.
- W2903157059 cites W2964121744 @default.
- W2903157059 cites W2986780196 @default.
- W2903157059 cites W648143168 @default.
- W2903157059 hasPublicationYear "2018" @default.
- W2903157059 type Work @default.
- W2903157059 sameAs 2903157059 @default.
- W2903157059 citedByCount "1" @default.
- W2903157059 countsByYear W29031570592018 @default.
- W2903157059 crossrefType "posted-content" @default.
- W2903157059 hasAuthorship W2903157059A5016753399 @default.
- W2903157059 hasAuthorship W2903157059A5040500007 @default.
- W2903157059 hasAuthorship W2903157059A5062576796 @default.
- W2903157059 hasAuthorship W2903157059A5087679173 @default.
- W2903157059 hasConcept C104317684 @default.
- W2903157059 hasConcept C108583219 @default.
- W2903157059 hasConcept C115961682 @default.
- W2903157059 hasConcept C121332964 @default.
- W2903157059 hasConcept C144024400 @default.
- W2903157059 hasConcept C154945302 @default.
- W2903157059 hasConcept C157202957 @default.
- W2903157059 hasConcept C185592680 @default.
- W2903157059 hasConcept C204321447 @default.
- W2903157059 hasConcept C24890656 @default.
- W2903157059 hasConcept C2776674983 @default.
- W2903157059 hasConcept C2778355321 @default.
- W2903157059 hasConcept C2779304628 @default.
- W2903157059 hasConcept C2988773926 @default.
- W2903157059 hasConcept C36289849 @default.
- W2903157059 hasConcept C39890363 @default.
- W2903157059 hasConcept C41008148 @default.
- W2903157059 hasConcept C50644808 @default.
- W2903157059 hasConcept C55493867 @default.
- W2903157059 hasConcept C63479239 @default.
- W2903157059 hasConceptScore W2903157059C104317684 @default.
- W2903157059 hasConceptScore W2903157059C108583219 @default.
- W2903157059 hasConceptScore W2903157059C115961682 @default.
- W2903157059 hasConceptScore W2903157059C121332964 @default.
- W2903157059 hasConceptScore W2903157059C144024400 @default.
- W2903157059 hasConceptScore W2903157059C154945302 @default.
- W2903157059 hasConceptScore W2903157059C157202957 @default.
- W2903157059 hasConceptScore W2903157059C185592680 @default.
- W2903157059 hasConceptScore W2903157059C204321447 @default.
- W2903157059 hasConceptScore W2903157059C24890656 @default.
- W2903157059 hasConceptScore W2903157059C2776674983 @default.
- W2903157059 hasConceptScore W2903157059C2778355321 @default.
- W2903157059 hasConceptScore W2903157059C2779304628 @default.
- W2903157059 hasConceptScore W2903157059C2988773926 @default.
- W2903157059 hasConceptScore W2903157059C36289849 @default.
- W2903157059 hasConceptScore W2903157059C39890363 @default.
- W2903157059 hasConceptScore W2903157059C41008148 @default.
- W2903157059 hasConceptScore W2903157059C50644808 @default.
- W2903157059 hasConceptScore W2903157059C55493867 @default.
- W2903157059 hasConceptScore W2903157059C63479239 @default.
- W2903157059 hasLocation W29031570591 @default.
- W2903157059 hasOpenAccess W2903157059 @default.
- W2903157059 hasPrimaryLocation W29031570591 @default.
- W2903157059 hasRelatedWork W1776042733 @default.
- W2903157059 hasRelatedWork W2123024445 @default.