Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048423054> ?p ?o ?g. }
- W3048423054 abstract "Accurate modeling of 3D objects exhibiting transparency, reflections and thin structures is an extremely challenging problem. Inspired by billboards and geometric proxies used in computer graphics, this paper proposes Generative Latent Textured Objects (GeLaTO), a compact representation that combines a set of coarse shape proxies defining low frequency geometry with learned neural textures, to encode both medium and fine scale geometry as well as view-dependent appearance. To generate the proxies' textures, we learn a joint latent space allowing category-level appearance and geometry interpolation. The proxies are independently rasterized with their corresponding neural texture and composited using a U-Net, which generates an output photorealistic image including an alpha map. We demonstrate the effectiveness of our approach by reconstructing complex objects from a sparse set of views. We show results on a dataset of real images of eyeglasses frames, which are particularly challenging to reconstruct using classical methods. We also demonstrate that these coarse proxies can be handcrafted when the underlying object geometry is easy to model, like eyeglasses, or generated using a neural network for more complex categories, such as cars." @default.
- W3048423054 created "2020-08-18" @default.
- W3048423054 creator A5016917903 @default.
- W3048423054 creator A5054383242 @default.
- W3048423054 creator A5061712514 @default.
- W3048423054 creator A5091132026 @default.
- W3048423054 creator A5091387733 @default.
- W3048423054 date "2020-08-11" @default.
- W3048423054 modified "2023-09-27" @default.
- W3048423054 title "GeLaTO: Generative Latent Textured Objects" @default.
- W3048423054 cites W1522301498 @default.
- W3048423054 cites W1585305924 @default.
- W3048423054 cites W1893912098 @default.
- W3048423054 cites W1901129140 @default.
- W3048423054 cites W1965356738 @default.
- W3048423054 cites W1997057955 @default.
- W3048423054 cites W2035773017 @default.
- W3048423054 cites W2037242534 @default.
- W3048423054 cites W2067166017 @default.
- W3048423054 cites W2080629029 @default.
- W3048423054 cites W2090614795 @default.
- W3048423054 cites W2124600577 @default.
- W3048423054 cites W2129404737 @default.
- W3048423054 cites W2190691619 @default.
- W3048423054 cites W2237250383 @default.
- W3048423054 cites W2331128040 @default.
- W3048423054 cites W2746030901 @default.
- W3048423054 cites W2811180360 @default.
- W3048423054 cites W2811426698 @default.
- W3048423054 cites W2902357748 @default.
- W3048423054 cites W2902492297 @default.
- W3048423054 cites W2903200123 @default.
- W3048423054 cites W2942074357 @default.
- W3048423054 cites W2949825757 @default.
- W3048423054 cites W2951004968 @default.
- W3048423054 cites W2951655307 @default.
- W3048423054 cites W2951856026 @default.
- W3048423054 cites W2951881930 @default.
- W3048423054 cites W2962770929 @default.
- W3048423054 cites W2962849139 @default.
- W3048423054 cites W2963073614 @default.
- W3048423054 cites W2963238691 @default.
- W3048423054 cites W2963376432 @default.
- W3048423054 cites W2963627347 @default.
- W3048423054 cites W2963850211 @default.
- W3048423054 cites W2963926543 @default.
- W3048423054 cites W2968257580 @default.
- W3048423054 cites W2969485315 @default.
- W3048423054 cites W2971278627 @default.
- W3048423054 cites W2982024234 @default.
- W3048423054 cites W2985068832 @default.
- W3048423054 cites W3011537551 @default.
- W3048423054 cites W3043139608 @default.
- W3048423054 cites W3100398946 @default.
- W3048423054 cites W3122589227 @default.
- W3048423054 hasPublicationYear "2020" @default.
- W3048423054 type Work @default.
- W3048423054 sameAs 3048423054 @default.
- W3048423054 citedByCount "0" @default.
- W3048423054 crossrefType "posted-content" @default.
- W3048423054 hasAuthorship W3048423054A5016917903 @default.
- W3048423054 hasAuthorship W3048423054A5054383242 @default.
- W3048423054 hasAuthorship W3048423054A5061712514 @default.
- W3048423054 hasAuthorship W3048423054A5091132026 @default.
- W3048423054 hasAuthorship W3048423054A5091387733 @default.
- W3048423054 hasConcept C115961682 @default.
- W3048423054 hasConcept C121684516 @default.
- W3048423054 hasConcept C137800194 @default.
- W3048423054 hasConcept C153180895 @default.
- W3048423054 hasConcept C154945302 @default.
- W3048423054 hasConcept C167966045 @default.
- W3048423054 hasConcept C177264268 @default.
- W3048423054 hasConcept C17744445 @default.
- W3048423054 hasConcept C199360897 @default.
- W3048423054 hasConcept C199539241 @default.
- W3048423054 hasConcept C21442007 @default.
- W3048423054 hasConcept C2776359362 @default.
- W3048423054 hasConcept C2781195486 @default.
- W3048423054 hasConcept C2781238097 @default.
- W3048423054 hasConcept C31972630 @default.
- W3048423054 hasConcept C39890363 @default.
- W3048423054 hasConcept C41008148 @default.
- W3048423054 hasConcept C50644808 @default.
- W3048423054 hasConcept C94625758 @default.
- W3048423054 hasConceptScore W3048423054C115961682 @default.
- W3048423054 hasConceptScore W3048423054C121684516 @default.
- W3048423054 hasConceptScore W3048423054C137800194 @default.
- W3048423054 hasConceptScore W3048423054C153180895 @default.
- W3048423054 hasConceptScore W3048423054C154945302 @default.
- W3048423054 hasConceptScore W3048423054C167966045 @default.
- W3048423054 hasConceptScore W3048423054C177264268 @default.
- W3048423054 hasConceptScore W3048423054C17744445 @default.
- W3048423054 hasConceptScore W3048423054C199360897 @default.
- W3048423054 hasConceptScore W3048423054C199539241 @default.
- W3048423054 hasConceptScore W3048423054C21442007 @default.
- W3048423054 hasConceptScore W3048423054C2776359362 @default.
- W3048423054 hasConceptScore W3048423054C2781195486 @default.
- W3048423054 hasConceptScore W3048423054C2781238097 @default.
- W3048423054 hasConceptScore W3048423054C31972630 @default.
- W3048423054 hasConceptScore W3048423054C39890363 @default.