Matches in SemOpenAlex for { <https://semopenalex.org/work/W3123674811> ?p ?o ?g. }
- W3123674811 endingPage "2285" @default.
- W3123674811 startingPage "2277" @default.
- W3123674811 abstract "In this paper, a novel learning-based network, named DeepDT, is proposed to reconstruct the surface from Delaunay triangulation of point cloud. DeepDT learns to predict inside/outside labels of Delaunay tetrahedrons directly from a point cloud and corresponding Delaunay triangulation. The local geometry features are first extracted from the input point cloud and aggregated into a graph deriving from the Delaunay triangulation. Then a graph filtering is applied on the aggregated features in order to add structural regularization to the label prediction of tetrahedrons. Due to the complicated spatial relations between tetrahedrons and the triangles, it is impossible to directly generate ground truth labels of tetrahedrons from ground truth surface. Therefore, we propose a multi-label supervision strategy which votes for the label of a tetrahedron with labels of sampling locations inside it. The proposed DeepDT can maintain abundant geometry details without generating overly complex surfaces, especially for inner surfaces of open scenes. Meanwhile, the generalization ability and time consumption of the proposed method is acceptable and competitive compared with the state-of-the-art methods. Experiments demonstrate the superior performance of the proposed DeepDT." @default.
- W3123674811 created "2021-02-01" @default.
- W3123674811 creator A5005276789 @default.
- W3123674811 creator A5051754127 @default.
- W3123674811 creator A5087239641 @default.
- W3123674811 date "2021-05-18" @default.
- W3123674811 modified "2023-10-11" @default.
- W3123674811 title "DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction" @default.
- W3123674811 cites W1969204979 @default.
- W3123674811 cites W1970883308 @default.
- W3123674811 cites W1971748934 @default.
- W3123674811 cites W1977758817 @default.
- W3123674811 cites W1992642990 @default.
- W3123674811 cites W2000081328 @default.
- W3123674811 cites W2005686772 @default.
- W3123674811 cites W2006213557 @default.
- W3123674811 cites W2008073424 @default.
- W3123674811 cites W2009422376 @default.
- W3123674811 cites W2029041800 @default.
- W3123674811 cites W2057408700 @default.
- W3123674811 cites W2085905957 @default.
- W3123674811 cites W2100816864 @default.
- W3123674811 cites W2111240761 @default.
- W3123674811 cites W2139331573 @default.
- W3123674811 cites W2142792228 @default.
- W3123674811 cites W2165306775 @default.
- W3123674811 cites W2170167721 @default.
- W3123674811 cites W2190691619 @default.
- W3123674811 cites W2229412420 @default.
- W3123674811 cites W2519887557 @default.
- W3123674811 cites W2556802233 @default.
- W3123674811 cites W2559882727 @default.
- W3123674811 cites W2609754928 @default.
- W3123674811 cites W2798670728 @default.
- W3123674811 cites W2885317998 @default.
- W3123674811 cites W2888719953 @default.
- W3123674811 cites W2895524927 @default.
- W3123674811 cites W2922511813 @default.
- W3123674811 cites W2963627347 @default.
- W3123674811 cites W2963926543 @default.
- W3123674811 cites W3035292206 @default.
- W3123674811 cites W3035591705 @default.
- W3123674811 cites W3110030735 @default.
- W3123674811 doi "https://doi.org/10.1609/aaai.v35i3.16327" @default.
- W3123674811 hasPublicationYear "2021" @default.
- W3123674811 type Work @default.
- W3123674811 sameAs 3123674811 @default.
- W3123674811 citedByCount "11" @default.
- W3123674811 countsByYear W31236748112020 @default.
- W3123674811 countsByYear W31236748112022 @default.
- W3123674811 countsByYear W31236748112023 @default.
- W3123674811 crossrefType "journal-article" @default.
- W3123674811 hasAuthorship W3123674811A5005276789 @default.
- W3123674811 hasAuthorship W3123674811A5051754127 @default.
- W3123674811 hasAuthorship W3123674811A5087239641 @default.
- W3123674811 hasBestOaLocation W31236748111 @default.
- W3123674811 hasConcept C105239961 @default.
- W3123674811 hasConcept C11413529 @default.
- W3123674811 hasConcept C121198538 @default.
- W3123674811 hasConcept C128321387 @default.
- W3123674811 hasConcept C131979681 @default.
- W3123674811 hasConcept C146849305 @default.
- W3123674811 hasConcept C154945302 @default.
- W3123674811 hasConcept C167117609 @default.
- W3123674811 hasConcept C178609930 @default.
- W3123674811 hasConcept C183342303 @default.
- W3123674811 hasConcept C20885615 @default.
- W3123674811 hasConcept C2524010 @default.
- W3123674811 hasConcept C2776799497 @default.
- W3123674811 hasConcept C31972630 @default.
- W3123674811 hasConcept C33923547 @default.
- W3123674811 hasConcept C41008148 @default.
- W3123674811 hasConcept C68010082 @default.
- W3123674811 hasConceptScore W3123674811C105239961 @default.
- W3123674811 hasConceptScore W3123674811C11413529 @default.
- W3123674811 hasConceptScore W3123674811C121198538 @default.
- W3123674811 hasConceptScore W3123674811C128321387 @default.
- W3123674811 hasConceptScore W3123674811C131979681 @default.
- W3123674811 hasConceptScore W3123674811C146849305 @default.
- W3123674811 hasConceptScore W3123674811C154945302 @default.
- W3123674811 hasConceptScore W3123674811C167117609 @default.
- W3123674811 hasConceptScore W3123674811C178609930 @default.
- W3123674811 hasConceptScore W3123674811C183342303 @default.
- W3123674811 hasConceptScore W3123674811C20885615 @default.
- W3123674811 hasConceptScore W3123674811C2524010 @default.
- W3123674811 hasConceptScore W3123674811C2776799497 @default.
- W3123674811 hasConceptScore W3123674811C31972630 @default.
- W3123674811 hasConceptScore W3123674811C33923547 @default.
- W3123674811 hasConceptScore W3123674811C41008148 @default.
- W3123674811 hasConceptScore W3123674811C68010082 @default.
- W3123674811 hasIssue "3" @default.
- W3123674811 hasLocation W31236748111 @default.
- W3123674811 hasLocation W31236748112 @default.
- W3123674811 hasOpenAccess W3123674811 @default.
- W3123674811 hasPrimaryLocation W31236748111 @default.
- W3123674811 hasRelatedWork W1979940344 @default.
- W3123674811 hasRelatedWork W2018303226 @default.
- W3123674811 hasRelatedWork W2036500909 @default.