Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306404483> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4306404483 endingPage "2148" @default.
- W4306404483 startingPage "2148" @default.
- W4306404483 abstract "Recently, learning-based image completion methods have made encouraging progress on square or irregular masks. The generative adversarial networks (GANs) have been able to produce visually realistic and semantically correct results. However, much texture and structure information will be lost in the completion process. If the missing part is too large to provide useful information, the result will be ambiguity, residual shadow, and object confusion. In order to complete large mask images, we present a novel model using conditional GAN called coarse-to-fine condition GAN (CF CGAN). We use a coarse-to-fine generator with symmetry and new perceptual loss based on VGG-16. The generator is symmetric in structure. For large mask image completion, our method produces visually realistic and semantically correct results. The generalization ability of our model is also excellent. We evaluate our model on the CelebA dataset and use FID, LPIPS, and SSIM as the metrics. Experiments demonstrate superior performance in terms of both quality and reality in free-form image completion." @default.
- W4306404483 created "2022-10-17" @default.
- W4306404483 creator A5022526821 @default.
- W4306404483 creator A5047916176 @default.
- W4306404483 creator A5048396052 @default.
- W4306404483 creator A5056483998 @default.
- W4306404483 date "2022-10-14" @default.
- W4306404483 modified "2023-10-18" @default.
- W4306404483 title "Large Mask Image Completion with Conditional GAN" @default.
- W4306404483 cites W2064076387 @default.
- W4306404483 cites W2103504761 @default.
- W4306404483 cites W2105038642 @default.
- W4306404483 cites W2738588019 @default.
- W4306404483 cites W2799277064 @default.
- W4306404483 cites W2963920537 @default.
- W4306404483 cites W3190905475 @default.
- W4306404483 cites W3202244870 @default.
- W4306404483 cites W4229079333 @default.
- W4306404483 cites W4240726888 @default.
- W4306404483 cites W4286502880 @default.
- W4306404483 cites W4289861079 @default.
- W4306404483 doi "https://doi.org/10.3390/sym14102148" @default.
- W4306404483 hasPublicationYear "2022" @default.
- W4306404483 type Work @default.
- W4306404483 citedByCount "2" @default.
- W4306404483 countsByYear W43064044832023 @default.
- W4306404483 crossrefType "journal-article" @default.
- W4306404483 hasAuthorship W4306404483A5022526821 @default.
- W4306404483 hasAuthorship W4306404483A5047916176 @default.
- W4306404483 hasAuthorship W4306404483A5048396052 @default.
- W4306404483 hasAuthorship W4306404483A5056483998 @default.
- W4306404483 hasBestOaLocation W43064044831 @default.
- W4306404483 hasConcept C111919701 @default.
- W4306404483 hasConcept C11413529 @default.
- W4306404483 hasConcept C115961682 @default.
- W4306404483 hasConcept C121332964 @default.
- W4306404483 hasConcept C134306372 @default.
- W4306404483 hasConcept C153180895 @default.
- W4306404483 hasConcept C154945302 @default.
- W4306404483 hasConcept C155512373 @default.
- W4306404483 hasConcept C163258240 @default.
- W4306404483 hasConcept C177148314 @default.
- W4306404483 hasConcept C200873422 @default.
- W4306404483 hasConcept C2779803651 @default.
- W4306404483 hasConcept C2780992000 @default.
- W4306404483 hasConcept C31972630 @default.
- W4306404483 hasConcept C33923547 @default.
- W4306404483 hasConcept C41008148 @default.
- W4306404483 hasConcept C62520636 @default.
- W4306404483 hasConcept C76155785 @default.
- W4306404483 hasConcept C94915269 @default.
- W4306404483 hasConcept C98045186 @default.
- W4306404483 hasConceptScore W4306404483C111919701 @default.
- W4306404483 hasConceptScore W4306404483C11413529 @default.
- W4306404483 hasConceptScore W4306404483C115961682 @default.
- W4306404483 hasConceptScore W4306404483C121332964 @default.
- W4306404483 hasConceptScore W4306404483C134306372 @default.
- W4306404483 hasConceptScore W4306404483C153180895 @default.
- W4306404483 hasConceptScore W4306404483C154945302 @default.
- W4306404483 hasConceptScore W4306404483C155512373 @default.
- W4306404483 hasConceptScore W4306404483C163258240 @default.
- W4306404483 hasConceptScore W4306404483C177148314 @default.
- W4306404483 hasConceptScore W4306404483C200873422 @default.
- W4306404483 hasConceptScore W4306404483C2779803651 @default.
- W4306404483 hasConceptScore W4306404483C2780992000 @default.
- W4306404483 hasConceptScore W4306404483C31972630 @default.
- W4306404483 hasConceptScore W4306404483C33923547 @default.
- W4306404483 hasConceptScore W4306404483C41008148 @default.
- W4306404483 hasConceptScore W4306404483C62520636 @default.
- W4306404483 hasConceptScore W4306404483C76155785 @default.
- W4306404483 hasConceptScore W4306404483C94915269 @default.
- W4306404483 hasConceptScore W4306404483C98045186 @default.
- W4306404483 hasFunder F4320321001 @default.
- W4306404483 hasIssue "10" @default.
- W4306404483 hasLocation W43064044831 @default.
- W4306404483 hasOpenAccess W4306404483 @default.
- W4306404483 hasPrimaryLocation W43064044831 @default.
- W4306404483 hasRelatedWork W2904326725 @default.
- W4306404483 hasRelatedWork W2904616728 @default.
- W4306404483 hasRelatedWork W2946952476 @default.
- W4306404483 hasRelatedWork W2975513049 @default.
- W4306404483 hasRelatedWork W2977027504 @default.
- W4306404483 hasRelatedWork W4224217118 @default.
- W4306404483 hasRelatedWork W4283584549 @default.
- W4306404483 hasRelatedWork W4289145824 @default.
- W4306404483 hasRelatedWork W4301908144 @default.
- W4306404483 hasRelatedWork W4308217387 @default.
- W4306404483 hasVolume "14" @default.
- W4306404483 isParatext "false" @default.
- W4306404483 isRetracted "false" @default.
- W4306404483 workType "article" @default.