Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210368713> ?p ?o ?g. }
- W4210368713 endingPage "963" @default.
- W4210368713 startingPage "946" @default.
- W4210368713 abstract "Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets." @default.
- W4210368713 created "2022-02-08" @default.
- W4210368713 creator A5000619646 @default.
- W4210368713 creator A5009075067 @default.
- W4210368713 creator A5015482478 @default.
- W4210368713 creator A5028467654 @default.
- W4210368713 creator A5031202827 @default.
- W4210368713 creator A5042241049 @default.
- W4210368713 creator A5049321721 @default.
- W4210368713 creator A5051555459 @default.
- W4210368713 creator A5061696740 @default.
- W4210368713 date "2023-01-01" @default.
- W4210368713 modified "2023-10-16" @default.
- W4210368713 title "Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds" @default.
- W4210368713 cites W19756496 @default.
- W4210368713 cites W1986465719 @default.
- W4210368713 cites W1987113397 @default.
- W4210368713 cites W2004402003 @default.
- W4210368713 cites W2010473040 @default.
- W4210368713 cites W2029041800 @default.
- W4210368713 cites W2043228434 @default.
- W4210368713 cites W2052790699 @default.
- W4210368713 cites W2058524213 @default.
- W4210368713 cites W2072723786 @default.
- W4210368713 cites W2081750044 @default.
- W4210368713 cites W2084595284 @default.
- W4210368713 cites W2100816864 @default.
- W4210368713 cites W2112477742 @default.
- W4210368713 cites W2136154655 @default.
- W4210368713 cites W2157950344 @default.
- W4210368713 cites W2199460564 @default.
- W4210368713 cites W2551040565 @default.
- W4210368713 cites W2766448241 @default.
- W4210368713 cites W2790597870 @default.
- W4210368713 cites W2799893270 @default.
- W4210368713 cites W2805499196 @default.
- W4210368713 cites W2945485418 @default.
- W4210368713 cites W2945811816 @default.
- W4210368713 cites W2948921918 @default.
- W4210368713 cites W2963026027 @default.
- W4210368713 cites W2963312728 @default.
- W4210368713 cites W2963515086 @default.
- W4210368713 cites W2963719584 @default.
- W4210368713 cites W2963756608 @default.
- W4210368713 cites W2969633497 @default.
- W4210368713 cites W2979750740 @default.
- W4210368713 cites W2982648348 @default.
- W4210368713 cites W2988577506 @default.
- W4210368713 cites W3003775208 @default.
- W4210368713 cites W3009072206 @default.
- W4210368713 cites W3021053382 @default.
- W4210368713 cites W3034261725 @default.
- W4210368713 cites W3034986117 @default.
- W4210368713 cites W3035145671 @default.
- W4210368713 cites W3035542908 @default.
- W4210368713 cites W3045414484 @default.
- W4210368713 cites W3091189374 @default.
- W4210368713 cites W3101395346 @default.
- W4210368713 cites W3106699132 @default.
- W4210368713 cites W3122159272 @default.
- W4210368713 cites W3126922312 @default.
- W4210368713 cites W3128252107 @default.
- W4210368713 cites W3137369665 @default.
- W4210368713 cites W3146210588 @default.
- W4210368713 cites W4229976114 @default.
- W4210368713 doi "https://doi.org/10.1109/tpami.2022.3145877" @default.
- W4210368713 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35077361" @default.
- W4210368713 hasPublicationYear "2023" @default.
- W4210368713 type Work @default.
- W4210368713 citedByCount "3" @default.
- W4210368713 countsByYear W42103687132023 @default.
- W4210368713 crossrefType "journal-article" @default.
- W4210368713 hasAuthorship W4210368713A5000619646 @default.
- W4210368713 hasAuthorship W4210368713A5009075067 @default.
- W4210368713 hasAuthorship W4210368713A5015482478 @default.
- W4210368713 hasAuthorship W4210368713A5028467654 @default.
- W4210368713 hasAuthorship W4210368713A5031202827 @default.
- W4210368713 hasAuthorship W4210368713A5042241049 @default.
- W4210368713 hasAuthorship W4210368713A5049321721 @default.
- W4210368713 hasAuthorship W4210368713A5051555459 @default.
- W4210368713 hasAuthorship W4210368713A5061696740 @default.
- W4210368713 hasBestOaLocation W42103687132 @default.
- W4210368713 hasConcept C107673813 @default.
- W4210368713 hasConcept C111472728 @default.
- W4210368713 hasConcept C11413529 @default.
- W4210368713 hasConcept C118732077 @default.
- W4210368713 hasConcept C131979681 @default.
- W4210368713 hasConcept C138885662 @default.
- W4210368713 hasConcept C14166107 @default.
- W4210368713 hasConcept C153180895 @default.
- W4210368713 hasConcept C154945302 @default.
- W4210368713 hasConcept C177769412 @default.
- W4210368713 hasConcept C189950617 @default.
- W4210368713 hasConcept C2524010 @default.
- W4210368713 hasConcept C2776401178 @default.
- W4210368713 hasConcept C2776799497 @default.
- W4210368713 hasConcept C28719098 @default.
- W4210368713 hasConcept C31972630 @default.