FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920223497> ?p ?o ?g. }

• W2920223497 endingPage "844" @default.
• W2920223497 startingPage "824" @default.
• W2920223497 abstract "Deep generative models have significantly advanced image generation, enabling generation of visually pleasing images with realistic texture. Apart from the texture, it is the shape geometry of objects that strongly dictates their appearance. However, currently available generative models do not incorporate geometric information into the image generation process. This often yields visual objects of degenerated quality. In this work, we propose a regularized Geometry-Aware Generative Adversarial Network (GAGAN) which disentangles appearance and shape in the latent space. This regularized GAGAN enables the generation of images with both realistic texture and shape. Specifically, we condition the generator on a statistical shape prior. The prior is enforced through mapping the generated images onto a canonical coordinate frame using a differentiable geometric transformation. In addition to incorporating geometric information, this constrains the search space and increases the model’s robustness. We show that our approach is versatile, able to generalise across domains (faces, sketches, hands and cats) and sample sizes (from as little as $$sim , 200{-}30{,}000$$ to more than 200, 000). We demonstrate superior performance through extensive quantitative and qualitative experiments in a variety of tasks and settings. Finally, we leverage our model to automatically and accurately detect errors or drifting in facial landmarks detection and tracking in-the-wild." @default.
• W2920223497 created "2019-03-11" @default.
• W2920223497 creator A5006048318 @default.
• W2920223497 creator A5016033078 @default.
• W2920223497 creator A5025839770 @default.
• W2920223497 creator A5050734738 @default.
• W2920223497 date "2019-03-02" @default.
• W2920223497 modified "2023-09-27" @default.
• W2920223497 title "Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks" @default.
• W2920223497 cites W1604643028 @default.
• W2920223497 cites W1724350370 @default.
• W2920223497 cites W1769974409 @default.
• W2920223497 cites W1834627138 @default.
• W2920223497 cites W2006318335 @default.
• W2920223497 cites W2006902452 @default.
• W2920223497 cites W2014322185 @default.
• W2920223497 cites W2025768430 @default.
• W2920223497 cites W2032558548 @default.
• W2920223497 cites W2038952578 @default.
• W2920223497 cites W2053584684 @default.
• W2920223497 cites W2058961190 @default.
• W2920223497 cites W2082308025 @default.
• W2920223497 cites W2099629511 @default.
• W2920223497 cites W2121058967 @default.
• W2920223497 cites W2130563197 @default.
• W2920223497 cites W2151103935 @default.
• W2920223497 cites W2152826865 @default.
• W2920223497 cites W2161969291 @default.
• W2920223497 cites W2163352848 @default.
• W2920223497 cites W2217448953 @default.
• W2920223497 cites W2280857173 @default.
• W2920223497 cites W2284800790 @default.
• W2920223497 cites W2331128040 @default.
• W2920223497 cites W2523270796 @default.
• W2920223497 cites W2564667781 @default.
• W2920223497 cites W2587982884 @default.
• W2920223497 cites W2740871496 @default.
• W2920223497 cites W2912990735 @default.
• W2920223497 cites W2962793481 @default.
• W2920223497 cites W2963420272 @default.
• W2920223497 cites W3104792420 @default.
• W2920223497 cites W2006352065 @default.
• W2920223497 doi "https://doi.org/10.1007/s11263-019-01155-7" @default.
• W2920223497 hasPublicationYear "2019" @default.
• W2920223497 type Work @default.
• W2920223497 sameAs 2920223497 @default.
• W2920223497 citedByCount "15" @default.
• W2920223497 countsByYear W29202234972019 @default.
• W2920223497 countsByYear W29202234972020 @default.
• W2920223497 countsByYear W29202234972021 @default.
• W2920223497 countsByYear W29202234972022 @default.
• W2920223497 countsByYear W29202234972023 @default.
• W2920223497 crossrefType "journal-article" @default.
• W2920223497 hasAuthorship W2920223497A5006048318 @default.
• W2920223497 hasAuthorship W2920223497A5016033078 @default.
• W2920223497 hasAuthorship W2920223497A5025839770 @default.
• W2920223497 hasAuthorship W2920223497A5050734738 @default.
• W2920223497 hasBestOaLocation W29202234971 @default.
• W2920223497 hasConcept C104317684 @default.
• W2920223497 hasConcept C112604564 @default.
• W2920223497 hasConcept C153083717 @default.
• W2920223497 hasConcept C153180895 @default.
• W2920223497 hasConcept C154945302 @default.
• W2920223497 hasConcept C185592680 @default.
• W2920223497 hasConcept C199360897 @default.
• W2920223497 hasConcept C2524010 @default.
• W2920223497 hasConcept C31972630 @default.
• W2920223497 hasConcept C33923547 @default.
• W2920223497 hasConcept C39890363 @default.
• W2920223497 hasConcept C41008148 @default.
• W2920223497 hasConcept C55493867 @default.
• W2920223497 hasConcept C63479239 @default.
• W2920223497 hasConcept C97686452 @default.
• W2920223497 hasConceptScore W2920223497C104317684 @default.
• W2920223497 hasConceptScore W2920223497C112604564 @default.
• W2920223497 hasConceptScore W2920223497C153083717 @default.
• W2920223497 hasConceptScore W2920223497C153180895 @default.
• W2920223497 hasConceptScore W2920223497C154945302 @default.
• W2920223497 hasConceptScore W2920223497C185592680 @default.
• W2920223497 hasConceptScore W2920223497C199360897 @default.
• W2920223497 hasConceptScore W2920223497C2524010 @default.
• W2920223497 hasConceptScore W2920223497C31972630 @default.
• W2920223497 hasConceptScore W2920223497C33923547 @default.
• W2920223497 hasConceptScore W2920223497C39890363 @default.
• W2920223497 hasConceptScore W2920223497C41008148 @default.
• W2920223497 hasConceptScore W2920223497C55493867 @default.
• W2920223497 hasConceptScore W2920223497C63479239 @default.
• W2920223497 hasConceptScore W2920223497C97686452 @default.
• W2920223497 hasFunder F4320332999 @default.
• W2920223497 hasIssue "6-7" @default.
• W2920223497 hasLocation W29202234971 @default.
• W2920223497 hasLocation W29202234972 @default.
• W2920223497 hasOpenAccess W2920223497 @default.
• W2920223497 hasPrimaryLocation W29202234971 @default.
• W2920223497 hasRelatedWork W1999222583 @default.
• W2920223497 hasRelatedWork W2035976912 @default.
• W2920223497 hasRelatedWork W2042311553 @default.
• W2920223497 hasRelatedWork W2109974539 @default.

• next