Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386417966> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4386417966 endingPage "4338" @default.
- W4386417966 startingPage "4338" @default.
- W4386417966 abstract "The integrity of a point cloud frequently suffers from discontinuous material surfaces or coarse sensor resolutions. Existing methods focus on reconstructing the overall structure, but salient points or small irregular surfaces are difficult to be predicted. Toward this issue, we propose a new end-to-end neural network for point cloud completion. To avoid non-uniform point density, the regular voxel centers are selected as reference points. The encoder and decoder are designed with Patchify, transformers, and multilayer perceptrons. An implicit classifier is incorporated in the decoder to mark the valid voxels that are allowed for diffusion after removing vacant grids from completion. With newly designed loss function, the classifier is trained to learn the contours, which helps to identify the grids that are difficult to be judged for diffusion. The effectiveness of the proposed model is validated in the experiments on the indoor ShapeNet dataset, the outdoor KITTI dataset, and the airbone laser dataset by competing with state-of-the-art methods, which show that our method can predict more accurate point coordinates with rich details and uniform point distributions." @default.
- W4386417966 created "2023-09-05" @default.
- W4386417966 creator A5026812631 @default.
- W4386417966 creator A5068500157 @default.
- W4386417966 creator A5083273144 @default.
- W4386417966 date "2023-09-03" @default.
- W4386417966 modified "2023-09-27" @default.
- W4386417966 title "Learning Contours for Point Cloud Completion" @default.
- W4386417966 cites W2150066425 @default.
- W4386417966 cites W2796426482 @default.
- W4386417966 cites W2886499109 @default.
- W4386417966 cites W2905288042 @default.
- W4386417966 cites W2953668091 @default.
- W4386417966 cites W2963071695 @default.
- W4386417966 cites W2964228567 @default.
- W4386417966 cites W2997088169 @default.
- W4386417966 cites W3025708905 @default.
- W4386417966 cites W3034584726 @default.
- W4386417966 cites W3035014292 @default.
- W4386417966 cites W3134499579 @default.
- W4386417966 cites W3170120958 @default.
- W4386417966 cites W3170469318 @default.
- W4386417966 cites W3170754649 @default.
- W4386417966 cites W3171030514 @default.
- W4386417966 cites W3173744995 @default.
- W4386417966 cites W3175702600 @default.
- W4386417966 cites W3183963759 @default.
- W4386417966 cites W3196231425 @default.
- W4386417966 cites W3197310284 @default.
- W4386417966 cites W4221143972 @default.
- W4386417966 cites W4232457899 @default.
- W4386417966 cites W4313156423 @default.
- W4386417966 doi "https://doi.org/10.3390/rs15174338" @default.
- W4386417966 hasPublicationYear "2023" @default.
- W4386417966 type Work @default.
- W4386417966 citedByCount "0" @default.
- W4386417966 crossrefType "journal-article" @default.
- W4386417966 hasAuthorship W4386417966A5026812631 @default.
- W4386417966 hasAuthorship W4386417966A5068500157 @default.
- W4386417966 hasAuthorship W4386417966A5083273144 @default.
- W4386417966 hasBestOaLocation W43864179661 @default.
- W4386417966 hasConcept C11413529 @default.
- W4386417966 hasConcept C131979681 @default.
- W4386417966 hasConcept C153180895 @default.
- W4386417966 hasConcept C154945302 @default.
- W4386417966 hasConcept C2780719617 @default.
- W4386417966 hasConcept C31972630 @default.
- W4386417966 hasConcept C41008148 @default.
- W4386417966 hasConcept C50644808 @default.
- W4386417966 hasConcept C54170458 @default.
- W4386417966 hasConcept C95623464 @default.
- W4386417966 hasConceptScore W4386417966C11413529 @default.
- W4386417966 hasConceptScore W4386417966C131979681 @default.
- W4386417966 hasConceptScore W4386417966C153180895 @default.
- W4386417966 hasConceptScore W4386417966C154945302 @default.
- W4386417966 hasConceptScore W4386417966C2780719617 @default.
- W4386417966 hasConceptScore W4386417966C31972630 @default.
- W4386417966 hasConceptScore W4386417966C41008148 @default.
- W4386417966 hasConceptScore W4386417966C50644808 @default.
- W4386417966 hasConceptScore W4386417966C54170458 @default.
- W4386417966 hasConceptScore W4386417966C95623464 @default.
- W4386417966 hasFunder F4320321001 @default.
- W4386417966 hasIssue "17" @default.
- W4386417966 hasLocation W43864179661 @default.
- W4386417966 hasOpenAccess W4386417966 @default.
- W4386417966 hasPrimaryLocation W43864179661 @default.
- W4386417966 hasRelatedWork W2160739731 @default.
- W4386417966 hasRelatedWork W2563096758 @default.
- W4386417966 hasRelatedWork W2580345890 @default.
- W4386417966 hasRelatedWork W2685530223 @default.
- W4386417966 hasRelatedWork W2979718872 @default.
- W4386417966 hasRelatedWork W3158534694 @default.
- W4386417966 hasRelatedWork W3206828132 @default.
- W4386417966 hasRelatedWork W4290774832 @default.
- W4386417966 hasRelatedWork W4293067784 @default.
- W4386417966 hasRelatedWork W2494681155 @default.
- W4386417966 hasVolume "15" @default.
- W4386417966 isParatext "false" @default.
- W4386417966 isRetracted "false" @default.
- W4386417966 workType "article" @default.