FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203197903> ?p ?o ?g. }

• W3203197903 endingPage "8367" @default.
• W3203197903 startingPage "8354" @default.
• W3203197903 abstract "This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes. To tackle this challenging issue, we propose a novel end-to-end learning-based framework. Specifically, by taking advantage of the linear approximation theorem, we first formulate the problem explicitly, which boils down to determining the interpolation weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted interpolation weights as well as the high-order refinements, by analyzing the local geometry of the input point cloud. The proposed method can be interpreted by the explicit formulation, and thus is more memory-efficient than existing ones. In sharp contrast to the existing methods that work only for a pre-defined and fixed upsampling factor, the proposed framework only requires a single neural network with one-time training to handle various upsampling factors within a typical range, which is highly desired in real-world applications. In addition, we propose a simple yet effective training strategy to drive such a flexible ability. In addition, our method can handle non-uniformly distributed and noisy data well. Extensive experiments on both synthetic and real-world data demonstrate the superiority of the proposed method over state-of-the-art methods both quantitatively and qualitatively. The code will be publicly available at https://github.com/ninaqy/Flexible-PU." @default.
• W3203197903 created "2021-10-11" @default.
• W3203197903 creator A5008386708 @default.
• W3203197903 creator A5015824704 @default.
• W3203197903 creator A5031957432 @default.
• W3203197903 creator A5045025757 @default.
• W3203197903 date "2021-01-01" @default.
• W3203197903 modified "2023-10-14" @default.
• W3203197903 title "Deep Magnification-Flexible Upsampling Over 3D Point Clouds" @default.
• W3203197903 cites W1987985833 @default.
• W3203197903 cites W1988317275 @default.
• W3203197903 cites W1992642990 @default.
• W3203197903 cites W2009622804 @default.
• W3203197903 cites W2025973801 @default.
• W3203197903 cites W2030080266 @default.
• W3203197903 cites W2041170980 @default.
• W3203197903 cites W2075821118 @default.
• W3203197903 cites W2078682181 @default.
• W3203197903 cites W2081194966 @default.
• W3203197903 cites W2094744861 @default.
• W3203197903 cites W2115579991 @default.
• W3203197903 cites W2119693472 @default.
• W3203197903 cites W2127310338 @default.
• W3203197903 cites W2137531922 @default.
• W3203197903 cites W2148821982 @default.
• W3203197903 cites W2154385726 @default.
• W3203197903 cites W2169611956 @default.
• W3203197903 cites W2345776828 @default.
• W3203197903 cites W2523398540 @default.
• W3203197903 cites W2530750588 @default.
• W3203197903 cites W2532511219 @default.
• W3203197903 cites W2555618208 @default.
• W3203197903 cites W2558294288 @default.
• W3203197903 cites W2560609797 @default.
• W3203197903 cites W2563408008 @default.
• W3203197903 cites W2597655663 @default.
• W3203197903 cites W2607041014 @default.
• W3203197903 cites W2784996692 @default.
• W3203197903 cites W2804078698 @default.
• W3203197903 cites W2883357174 @default.
• W3203197903 cites W2884154111 @default.
• W3203197903 cites W2889300857 @default.
• W3203197903 cites W2902302021 @default.
• W3203197903 cites W2949708697 @default.
• W3203197903 cites W2963031226 @default.
• W3203197903 cites W2963057320 @default.
• W3203197903 cites W2963121255 @default.
• W3203197903 cites W2963341956 @default.
• W3203197903 cites W2963390820 @default.
• W3203197903 cites W2963403868 @default.
• W3203197903 cites W2963680153 @default.
• W3203197903 cites W2964062501 @default.
• W3203197903 cites W2964101377 @default.
• W3203197903 cites W2964110616 @default.
• W3203197903 cites W2964121744 @default.
• W3203197903 cites W2964308564 @default.
• W3203197903 cites W2970389371 @default.
• W3203197903 cites W2970597249 @default.
• W3203197903 cites W2970633157 @default.
• W3203197903 cites W2979750740 @default.
• W3203197903 cites W2981440248 @default.
• W3203197903 cites W2983446232 @default.
• W3203197903 cites W2986382673 @default.
• W3203197903 cites W2988715931 @default.
• W3203197903 cites W2997337685 @default.
• W3203197903 cites W3034885317 @default.
• W3203197903 cites W3096609285 @default.
• W3203197903 cites W3104408604 @default.
• W3203197903 cites W3106699132 @default.
• W3203197903 cites W3128475240 @default.
• W3203197903 cites W3153465022 @default.
• W3203197903 cites W3175676582 @default.
• W3203197903 cites W3184736166 @default.
• W3203197903 doi "https://doi.org/10.1109/tip.2021.3115385" @default.
• W3203197903 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34591759" @default.
• W3203197903 hasPublicationYear "2021" @default.
• W3203197903 type Work @default.
• W3203197903 sameAs 3203197903 @default.
• W3203197903 citedByCount "18" @default.
• W3203197903 countsByYear W32031979032022 @default.
• W3203197903 countsByYear W32031979032023 @default.
• W3203197903 crossrefType "journal-article" @default.
• W3203197903 hasAuthorship W3203197903A5008386708 @default.
• W3203197903 hasAuthorship W3203197903A5015824704 @default.
• W3203197903 hasAuthorship W3203197903A5031957432 @default.
• W3203197903 hasAuthorship W3203197903A5045025757 @default.
• W3203197903 hasBestOaLocation W32031979032 @default.
• W3203197903 hasConcept C108583219 @default.
• W3203197903 hasConcept C110384440 @default.
• W3203197903 hasConcept C11413529 @default.
• W3203197903 hasConcept C115961682 @default.
• W3203197903 hasConcept C131979681 @default.
• W3203197903 hasConcept C137800194 @default.
• W3203197903 hasConcept C154945302 @default.
• W3203197903 hasConcept C159985019 @default.
• W3203197903 hasConcept C177264268 @default.
• W3203197903 hasConcept C192562407 @default.
• W3203197903 hasConcept C199360897 @default.

• next