Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297799094> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4297799094 abstract "Deep neural representations of 3D shapes as implicit functions have been shown to produce high fidelity models surpassing the resolution-memory trade-off faced by the explicit representations using meshes and point clouds. However, most such approaches focus on representing closed shapes. Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes. However, since the gradients of UDFs vanish on the surface, it is challenging to estimate local (differential) geometric properties like the normals and tangent planes which are needed for many downstream applications in vision and graphics. There are additional challenges in computing these properties efficiently with a low-memory footprint. This paper presents a novel approach that models such surfaces using a new class of implicit representations called the closest surface-point (CSP) representation. We show that CSP allows us to represent complex surfaces of any topology (open or closed) with high fidelity. It also allows for accurate and efficient computation of local geometric properties. We further demonstrate that it leads to efficient implementation of downstream algorithms like sphere-tracing for rendering the 3D surface as well as to create explicit mesh-based representations. Extensive experimental evaluation on the ShapeNet dataset validate the above contributions with results surpassing the state-of-the-art." @default.
- W4297799094 created "2022-10-01" @default.
- W4297799094 creator A5010395074 @default.
- W4297799094 creator A5015371248 @default.
- W4297799094 creator A5045790971 @default.
- W4297799094 creator A5062755809 @default.
- W4297799094 creator A5072243664 @default.
- W4297799094 creator A5081429561 @default.
- W4297799094 creator A5085553141 @default.
- W4297799094 date "2021-06-10" @default.
- W4297799094 modified "2023-09-24" @default.
- W4297799094 title "Deep Implicit Surface Point Prediction Networks" @default.
- W4297799094 doi "https://doi.org/10.48550/arxiv.2106.05779" @default.
- W4297799094 hasPublicationYear "2021" @default.
- W4297799094 type Work @default.
- W4297799094 citedByCount "0" @default.
- W4297799094 crossrefType "posted-content" @default.
- W4297799094 hasAuthorship W4297799094A5010395074 @default.
- W4297799094 hasAuthorship W4297799094A5015371248 @default.
- W4297799094 hasAuthorship W4297799094A5045790971 @default.
- W4297799094 hasAuthorship W4297799094A5062755809 @default.
- W4297799094 hasAuthorship W4297799094A5072243664 @default.
- W4297799094 hasAuthorship W4297799094A5081429561 @default.
- W4297799094 hasAuthorship W4297799094A5085553141 @default.
- W4297799094 hasBestOaLocation W42977990941 @default.
- W4297799094 hasConcept C111919701 @default.
- W4297799094 hasConcept C11413529 @default.
- W4297799094 hasConcept C114614502 @default.
- W4297799094 hasConcept C121684516 @default.
- W4297799094 hasConcept C131979681 @default.
- W4297799094 hasConcept C138187205 @default.
- W4297799094 hasConcept C154945302 @default.
- W4297799094 hasConcept C184720557 @default.
- W4297799094 hasConcept C205711294 @default.
- W4297799094 hasConcept C2524010 @default.
- W4297799094 hasConcept C2776799497 @default.
- W4297799094 hasConcept C31487907 @default.
- W4297799094 hasConcept C33923547 @default.
- W4297799094 hasConcept C41008148 @default.
- W4297799094 hasConcept C45374587 @default.
- W4297799094 hasConcept C74912251 @default.
- W4297799094 hasConceptScore W4297799094C111919701 @default.
- W4297799094 hasConceptScore W4297799094C11413529 @default.
- W4297799094 hasConceptScore W4297799094C114614502 @default.
- W4297799094 hasConceptScore W4297799094C121684516 @default.
- W4297799094 hasConceptScore W4297799094C131979681 @default.
- W4297799094 hasConceptScore W4297799094C138187205 @default.
- W4297799094 hasConceptScore W4297799094C154945302 @default.
- W4297799094 hasConceptScore W4297799094C184720557 @default.
- W4297799094 hasConceptScore W4297799094C205711294 @default.
- W4297799094 hasConceptScore W4297799094C2524010 @default.
- W4297799094 hasConceptScore W4297799094C2776799497 @default.
- W4297799094 hasConceptScore W4297799094C31487907 @default.
- W4297799094 hasConceptScore W4297799094C33923547 @default.
- W4297799094 hasConceptScore W4297799094C41008148 @default.
- W4297799094 hasConceptScore W4297799094C45374587 @default.
- W4297799094 hasConceptScore W4297799094C74912251 @default.
- W4297799094 hasLocation W42977990941 @default.
- W4297799094 hasOpenAccess W4297799094 @default.
- W4297799094 hasPrimaryLocation W42977990941 @default.
- W4297799094 hasRelatedWork W134684646 @default.
- W4297799094 hasRelatedWork W2043047960 @default.
- W4297799094 hasRelatedWork W2316810968 @default.
- W4297799094 hasRelatedWork W2356200721 @default.
- W4297799094 hasRelatedWork W2888879731 @default.
- W4297799094 hasRelatedWork W4304142394 @default.
- W4297799094 hasRelatedWork W4311878195 @default.
- W4297799094 hasRelatedWork W4312606103 @default.
- W4297799094 hasRelatedWork W4320505042 @default.
- W4297799094 hasRelatedWork W4323569054 @default.
- W4297799094 isParatext "false" @default.
- W4297799094 isRetracted "false" @default.
- W4297799094 workType "article" @default.