Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955409087> ?p ?o ?g. }
- W2955409087 abstract "Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g., jets or MLS surfaces), local or non-local averaging, or on statistical assumptions about the underlying noise model. In contrast, we develop a simple data-driven method for removing outliers and reducing noise in unordered point clouds. We base our approach on a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties in point clouds. Our method first classifies and discards outlier samples, and then estimates correction vectors that project noisy points onto the original clean surfaces. The approach is efficient and robust to varying amounts of noise and outliers, while being able to handle large densely-sampled point clouds. In our extensive evaluation, both on synthesic and real data, we show an increased robustness to strong noise levels compared to various state-of-the-art methods, enabling accurate surface reconstruction from extremely noisy real data obtained by range scans. Finally, the simplicity and universality of our approach makes it very easy to integrate in any existing geometry processing pipeline." @default.
- W2955409087 created "2019-07-12" @default.
- W2955409087 creator A5035017722 @default.
- W2955409087 creator A5057883284 @default.
- W2955409087 creator A5058170430 @default.
- W2955409087 creator A5072368950 @default.
- W2955409087 creator A5082849657 @default.
- W2955409087 date "2019-01-04" @default.
- W2955409087 modified "2023-09-27" @default.
- W2955409087 title "PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds" @default.
- W2955409087 cites W156975732 @default.
- W2955409087 cites W1594957066 @default.
- W2955409087 cites W1965432148 @default.
- W2955409087 cites W1992642990 @default.
- W2955409087 cites W1995050439 @default.
- W2955409087 cites W1997147589 @default.
- W2955409087 cites W2004402003 @default.
- W2955409087 cites W2010473040 @default.
- W2955409087 cites W2037133587 @default.
- W2955409087 cites W2048430744 @default.
- W2955409087 cites W2052790699 @default.
- W2955409087 cites W2058524213 @default.
- W2955409087 cites W2097073572 @default.
- W2955409087 cites W2116562246 @default.
- W2955409087 cites W2121886361 @default.
- W2955409087 cites W2137531922 @default.
- W2955409087 cites W2148952796 @default.
- W2955409087 cites W2153663612 @default.
- W2955409087 cites W2162450071 @default.
- W2955409087 cites W2169611956 @default.
- W2955409087 cites W2293263800 @default.
- W2955409087 cites W2366389387 @default.
- W2955409087 cites W2508457857 @default.
- W2955409087 cites W2546714150 @default.
- W2955409087 cites W2551040565 @default.
- W2955409087 cites W2558748708 @default.
- W2955409087 cites W2560293005 @default.
- W2955409087 cites W2560609797 @default.
- W2955409087 cites W2560722161 @default.
- W2955409087 cites W2566809385 @default.
- W2955409087 cites W2574952845 @default.
- W2955409087 cites W2613155248 @default.
- W2955409087 cites W2617121149 @default.
- W2955409087 cites W2623075562 @default.
- W2955409087 cites W2765223700 @default.
- W2955409087 cites W2789616359 @default.
- W2955409087 cites W2797301041 @default.
- W2955409087 cites W2805499196 @default.
- W2955409087 cites W2805729703 @default.
- W2955409087 cites W2930206194 @default.
- W2955409087 cites W2949608135 @default.
- W2955409087 cites W2962865163 @default.
- W2955409087 cites W2963021451 @default.
- W2955409087 cites W2963121255 @default.
- W2955409087 cites W2979750740 @default.
- W2955409087 cites W3098903961 @default.
- W2955409087 cites W40786246 @default.
- W2955409087 cites W603908379 @default.
- W2955409087 cites W951004695 @default.
- W2955409087 hasPublicationYear "2019" @default.
- W2955409087 type Work @default.
- W2955409087 sameAs 2955409087 @default.
- W2955409087 citedByCount "2" @default.
- W2955409087 countsByYear W29554090872020 @default.
- W2955409087 crossrefType "posted-content" @default.
- W2955409087 hasAuthorship W2955409087A5035017722 @default.
- W2955409087 hasAuthorship W2955409087A5057883284 @default.
- W2955409087 hasAuthorship W2955409087A5058170430 @default.
- W2955409087 hasAuthorship W2955409087A5072368950 @default.
- W2955409087 hasAuthorship W2955409087A5082849657 @default.
- W2955409087 hasConcept C104317684 @default.
- W2955409087 hasConcept C11413529 @default.
- W2955409087 hasConcept C115961682 @default.
- W2955409087 hasConcept C131979681 @default.
- W2955409087 hasConcept C153180895 @default.
- W2955409087 hasConcept C154945302 @default.
- W2955409087 hasConcept C163294075 @default.
- W2955409087 hasConcept C185592680 @default.
- W2955409087 hasConcept C31972630 @default.
- W2955409087 hasConcept C41008148 @default.
- W2955409087 hasConcept C55493867 @default.
- W2955409087 hasConcept C63479239 @default.
- W2955409087 hasConcept C739882 @default.
- W2955409087 hasConcept C79337645 @default.
- W2955409087 hasConcept C99498987 @default.
- W2955409087 hasConceptScore W2955409087C104317684 @default.
- W2955409087 hasConceptScore W2955409087C11413529 @default.
- W2955409087 hasConceptScore W2955409087C115961682 @default.
- W2955409087 hasConceptScore W2955409087C131979681 @default.
- W2955409087 hasConceptScore W2955409087C153180895 @default.
- W2955409087 hasConceptScore W2955409087C154945302 @default.
- W2955409087 hasConceptScore W2955409087C163294075 @default.
- W2955409087 hasConceptScore W2955409087C185592680 @default.
- W2955409087 hasConceptScore W2955409087C31972630 @default.
- W2955409087 hasConceptScore W2955409087C41008148 @default.
- W2955409087 hasConceptScore W2955409087C55493867 @default.
- W2955409087 hasConceptScore W2955409087C63479239 @default.
- W2955409087 hasConceptScore W2955409087C739882 @default.
- W2955409087 hasConceptScore W2955409087C79337645 @default.
- W2955409087 hasConceptScore W2955409087C99498987 @default.