Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318941306> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4318941306 endingPage "109366" @default.
- W4318941306 startingPage "109366" @default.
- W4318941306 abstract "As a simple, flexible and effective representation for objects, 3D point cloud has attracted more and more attention in recent years. However, raw point clouds obtained from 3D scanners or image-based reconstruction techniques are often contaminated with noise and outliers, which hinders downstream tasks such as object classification, surface reconstruction, and so on. Therefore, point cloud cleaning, i.e., removing noisy points and outliers from raw point cloud, is a prior step of most geometry processing workflows. The exiting techniques for point cloud cleaning usually include two stages, that is, discarding outliers at first, and then denoising the resulting point cloud. This two-stage process usually requires two different models, which is cumbersome to train and use. To solve this problem, a novel data driven method, named SSPCN (single-stage point cloud cleaning network), is proposed in this paper. SSPCN can simultaneously remove outliers and denoise a point cloud in a single model. Specifically, SSPCN is consisted of adaptive downsampling module, feature compensation module, upsampling module and coordinate reconstruction module. Given a raw point cloud as input, the downsampling module is first used to obtain a prefiltered point cloud subset and learn initial features of the subset. The feature compensation module is then utilized to learn accurate features from initial features. Next, the upsampling module upsamples the features to restore the original size of the point cloud. Last, the coordinate reconstruction module generates a cleaned point cloud from upsampled features. SSPCN is validated both on synthetic and real scanned data. Extensive experiments demonstrate that SSPCN outperforms state-of-the-art point cloud cleaning techniques in terms of quantitative metric and visual quality." @default.
- W4318941306 created "2023-02-03" @default.
- W4318941306 creator A5046810458 @default.
- W4318941306 creator A5060002817 @default.
- W4318941306 date "2023-06-01" @default.
- W4318941306 modified "2023-10-02" @default.
- W4318941306 title "A single-stage point cloud cleaning network for outlier removal and denoising" @default.
- W4318941306 cites W1988317275 @default.
- W4318941306 cites W2004402003 @default.
- W4318941306 cites W2056370875 @default.
- W4318941306 cites W2084023597 @default.
- W4318941306 cites W2135046489 @default.
- W4318941306 cites W2137531922 @default.
- W4318941306 cites W2162979765 @default.
- W4318941306 cites W2169611956 @default.
- W4318941306 cites W2546714150 @default.
- W4318941306 cites W2617121149 @default.
- W4318941306 cites W2885553657 @default.
- W4318941306 cites W2906788812 @default.
- W4318941306 cites W2979750740 @default.
- W4318941306 cites W2998456637 @default.
- W4318941306 cites W3039448353 @default.
- W4318941306 cites W3089927720 @default.
- W4318941306 cites W3107378443 @default.
- W4318941306 cites W3137466219 @default.
- W4318941306 cites W3196335228 @default.
- W4318941306 cites W3204185592 @default.
- W4318941306 cites W4205490894 @default.
- W4318941306 cites W940328677 @default.
- W4318941306 doi "https://doi.org/10.1016/j.patcog.2023.109366" @default.
- W4318941306 hasPublicationYear "2023" @default.
- W4318941306 type Work @default.
- W4318941306 citedByCount "1" @default.
- W4318941306 countsByYear W43189413062023 @default.
- W4318941306 crossrefType "journal-article" @default.
- W4318941306 hasAuthorship W4318941306A5046810458 @default.
- W4318941306 hasAuthorship W4318941306A5060002817 @default.
- W4318941306 hasConcept C110384440 @default.
- W4318941306 hasConcept C111919701 @default.
- W4318941306 hasConcept C115961682 @default.
- W4318941306 hasConcept C131979681 @default.
- W4318941306 hasConcept C138885662 @default.
- W4318941306 hasConcept C153180895 @default.
- W4318941306 hasConcept C154945302 @default.
- W4318941306 hasConcept C2776401178 @default.
- W4318941306 hasConcept C31972630 @default.
- W4318941306 hasConcept C41008148 @default.
- W4318941306 hasConcept C41895202 @default.
- W4318941306 hasConcept C79337645 @default.
- W4318941306 hasConcept C79974875 @default.
- W4318941306 hasConcept C99498987 @default.
- W4318941306 hasConceptScore W4318941306C110384440 @default.
- W4318941306 hasConceptScore W4318941306C111919701 @default.
- W4318941306 hasConceptScore W4318941306C115961682 @default.
- W4318941306 hasConceptScore W4318941306C131979681 @default.
- W4318941306 hasConceptScore W4318941306C138885662 @default.
- W4318941306 hasConceptScore W4318941306C153180895 @default.
- W4318941306 hasConceptScore W4318941306C154945302 @default.
- W4318941306 hasConceptScore W4318941306C2776401178 @default.
- W4318941306 hasConceptScore W4318941306C31972630 @default.
- W4318941306 hasConceptScore W4318941306C41008148 @default.
- W4318941306 hasConceptScore W4318941306C41895202 @default.
- W4318941306 hasConceptScore W4318941306C79337645 @default.
- W4318941306 hasConceptScore W4318941306C79974875 @default.
- W4318941306 hasConceptScore W4318941306C99498987 @default.
- W4318941306 hasLocation W43189413061 @default.
- W4318941306 hasOpenAccess W4318941306 @default.
- W4318941306 hasPrimaryLocation W43189413061 @default.
- W4318941306 hasRelatedWork W1504288058 @default.
- W4318941306 hasRelatedWork W2167293474 @default.
- W4318941306 hasRelatedWork W2331674254 @default.
- W4318941306 hasRelatedWork W2979718872 @default.
- W4318941306 hasRelatedWork W3042897387 @default.
- W4318941306 hasRelatedWork W3158534694 @default.
- W4318941306 hasRelatedWork W3206828132 @default.
- W4318941306 hasRelatedWork W4281251454 @default.
- W4318941306 hasRelatedWork W4290774832 @default.
- W4318941306 hasRelatedWork W4310007291 @default.
- W4318941306 hasVolume "138" @default.
- W4318941306 isParatext "false" @default.
- W4318941306 isRetracted "false" @default.
- W4318941306 workType "article" @default.