Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133749673> ?p ?o ?g. }
- W3133749673 endingPage "118" @default.
- W3133749673 startingPage "103" @default.
- W3133749673 abstract "AbstractPoint clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by learning-based point cloud processing methods. The network is fully-convolutional and can build complex hierarchies of features by dynamically constructing neighborhood graphs from similarity among the high-dimensional feature representations of the points. When coupled with a loss promoting proximity to the ideal surface, the proposed approach significantly outperforms state-of-the-art methods on a variety of metrics. In particular, it is able to improve in terms of Chamfer measure and of quality of the surface normals that can be estimated from the denoised data. We also show that it is especially robust both at high noise levels and in presence of structured noise such as the one encountered in real LiDAR scans. KeywordsPoint cloudDenoisingGraph neural network" @default.
- W3133749673 created "2021-03-15" @default.
- W3133749673 creator A5016675020 @default.
- W3133749673 creator A5034486931 @default.
- W3133749673 creator A5058182410 @default.
- W3133749673 creator A5062328236 @default.
- W3133749673 date "2020-01-01" @default.
- W3133749673 modified "2023-10-15" @default.
- W3133749673 title "Learning Graph-Convolutional Representations for Point Cloud Denoising" @default.
- W3133749673 cites W156975732 @default.
- W3133749673 cites W1987113397 @default.
- W3133749673 cites W2004402003 @default.
- W3133749673 cites W2010473040 @default.
- W3133749673 cites W2037642501 @default.
- W3133749673 cites W2052790699 @default.
- W3133749673 cites W2101491865 @default.
- W3133749673 cites W2137531922 @default.
- W3133749673 cites W2169611956 @default.
- W3133749673 cites W2508457857 @default.
- W3133749673 cites W2546714150 @default.
- W3133749673 cites W2558748708 @default.
- W3133749673 cites W2606202972 @default.
- W3133749673 cites W2617121149 @default.
- W3133749673 cites W2791092480 @default.
- W3133749673 cites W2805499196 @default.
- W3133749673 cites W2906788812 @default.
- W3133749673 cites W2963197375 @default.
- W3133749673 cites W2963756602 @default.
- W3133749673 cites W2964253597 @default.
- W3133749673 cites W2970279440 @default.
- W3133749673 cites W2979750740 @default.
- W3133749673 cites W3048092834 @default.
- W3133749673 cites W3102733014 @default.
- W3133749673 cites W3137369665 @default.
- W3133749673 cites W3137466219 @default.
- W3133749673 doi "https://doi.org/10.1007/978-3-030-58565-5_7" @default.
- W3133749673 hasPublicationYear "2020" @default.
- W3133749673 type Work @default.
- W3133749673 sameAs 3133749673 @default.
- W3133749673 citedByCount "18" @default.
- W3133749673 countsByYear W31337496732020 @default.
- W3133749673 countsByYear W31337496732021 @default.
- W3133749673 countsByYear W31337496732022 @default.
- W3133749673 countsByYear W31337496732023 @default.
- W3133749673 crossrefType "book-chapter" @default.
- W3133749673 hasAuthorship W3133749673A5016675020 @default.
- W3133749673 hasAuthorship W3133749673A5034486931 @default.
- W3133749673 hasAuthorship W3133749673A5058182410 @default.
- W3133749673 hasAuthorship W3133749673A5062328236 @default.
- W3133749673 hasBestOaLocation W31337496732 @default.
- W3133749673 hasConcept C108583219 @default.
- W3133749673 hasConcept C111919701 @default.
- W3133749673 hasConcept C115961682 @default.
- W3133749673 hasConcept C131979681 @default.
- W3133749673 hasConcept C132525143 @default.
- W3133749673 hasConcept C138885662 @default.
- W3133749673 hasConcept C153180895 @default.
- W3133749673 hasConcept C154945302 @default.
- W3133749673 hasConcept C163294075 @default.
- W3133749673 hasConcept C2776401178 @default.
- W3133749673 hasConcept C41008148 @default.
- W3133749673 hasConcept C41895202 @default.
- W3133749673 hasConcept C79974875 @default.
- W3133749673 hasConcept C80444323 @default.
- W3133749673 hasConcept C81363708 @default.
- W3133749673 hasConcept C99498987 @default.
- W3133749673 hasConceptScore W3133749673C108583219 @default.
- W3133749673 hasConceptScore W3133749673C111919701 @default.
- W3133749673 hasConceptScore W3133749673C115961682 @default.
- W3133749673 hasConceptScore W3133749673C131979681 @default.
- W3133749673 hasConceptScore W3133749673C132525143 @default.
- W3133749673 hasConceptScore W3133749673C138885662 @default.
- W3133749673 hasConceptScore W3133749673C153180895 @default.
- W3133749673 hasConceptScore W3133749673C154945302 @default.
- W3133749673 hasConceptScore W3133749673C163294075 @default.
- W3133749673 hasConceptScore W3133749673C2776401178 @default.
- W3133749673 hasConceptScore W3133749673C41008148 @default.
- W3133749673 hasConceptScore W3133749673C41895202 @default.
- W3133749673 hasConceptScore W3133749673C79974875 @default.
- W3133749673 hasConceptScore W3133749673C80444323 @default.
- W3133749673 hasConceptScore W3133749673C81363708 @default.
- W3133749673 hasConceptScore W3133749673C99498987 @default.
- W3133749673 hasLocation W31337496731 @default.
- W3133749673 hasLocation W31337496732 @default.
- W3133749673 hasOpenAccess W3133749673 @default.
- W3133749673 hasPrimaryLocation W31337496731 @default.
- W3133749673 hasRelatedWork W2088610186 @default.
- W3133749673 hasRelatedWork W2731899572 @default.
- W3133749673 hasRelatedWork W2732542196 @default.
- W3133749673 hasRelatedWork W2738221750 @default.
- W3133749673 hasRelatedWork W2760085659 @default.
- W3133749673 hasRelatedWork W3116150086 @default.
- W3133749673 hasRelatedWork W3133861977 @default.
- W3133749673 hasRelatedWork W3156786002 @default.
- W3133749673 hasRelatedWork W3186111093 @default.
- W3133749673 hasRelatedWork W4200173597 @default.
- W3133749673 isParatext "false" @default.
- W3133749673 isRetracted "false" @default.