Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207658203> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3207658203 abstract "Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth. To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images. Specifically, we first propose a neighbor expansion unit (NEU) to upsample the sparse point clouds, where the local geometric structures of the sparse point clouds are exploited to learn weights for point interpolation. Then, we develop a differentiable point cloud rendering unit (DRU) as an end-to-end module in our network to render the point cloud into multi-view images. Finally, we formulate a shape-consistent loss and an image-consistent loss to train the network so that the shapes of the sparse and dense point clouds are as consistent as possible. Extensive results on the CAD and scanned datasets demonstrate that our method can achieve impressive results in a self-supervised manner." @default.
- W3207658203 created "2021-10-25" @default.
- W3207658203 creator A5030769176 @default.
- W3207658203 creator A5063066022 @default.
- W3207658203 creator A5089409762 @default.
- W3207658203 date "2021-10-17" @default.
- W3207658203 modified "2023-09-30" @default.
- W3207658203 title "SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering" @default.
- W3207658203 cites W1985907520 @default.
- W3207658203 cites W2025973801 @default.
- W3207658203 cites W2115579991 @default.
- W3207658203 cites W2137531922 @default.
- W3207658203 cites W2169611956 @default.
- W3207658203 cites W2342511487 @default.
- W3207658203 cites W2544193809 @default.
- W3207658203 cites W2558027072 @default.
- W3207658203 cites W2565356621 @default.
- W3207658203 cites W2610248394 @default.
- W3207658203 cites W2769157872 @default.
- W3207658203 cites W2796822548 @default.
- W3207658203 cites W2798291180 @default.
- W3207658203 cites W2799123546 @default.
- W3207658203 cites W2802030532 @default.
- W3207658203 cites W2811490555 @default.
- W3207658203 cites W2872491670 @default.
- W3207658203 cites W2886499109 @default.
- W3207658203 cites W2891345365 @default.
- W3207658203 cites W2902812770 @default.
- W3207658203 cites W2954174912 @default.
- W3207658203 cites W2955544543 @default.
- W3207658203 cites W2960986959 @default.
- W3207658203 cites W2963053547 @default.
- W3207658203 cites W2963390820 @default.
- W3207658203 cites W2963527086 @default.
- W3207658203 cites W2963680153 @default.
- W3207658203 cites W2963708168 @default.
- W3207658203 cites W2967053680 @default.
- W3207658203 cites W2979750740 @default.
- W3207658203 cites W2986519585 @default.
- W3207658203 cites W2986615800 @default.
- W3207658203 cites W2990173985 @default.
- W3207658203 cites W2997337685 @default.
- W3207658203 cites W3015217705 @default.
- W3207658203 cites W3035398346 @default.
- W3207658203 cites W3036259090 @default.
- W3207658203 cites W3089903748 @default.
- W3207658203 cites W3089947940 @default.
- W3207658203 cites W3098881644 @default.
- W3207658203 cites W3106699132 @default.
- W3207658203 cites W3108944788 @default.
- W3207658203 cites W3137466219 @default.
- W3207658203 doi "https://doi.org/10.1145/3474085.3475381" @default.
- W3207658203 hasPublicationYear "2021" @default.
- W3207658203 type Work @default.
- W3207658203 sameAs 3207658203 @default.
- W3207658203 citedByCount "9" @default.
- W3207658203 countsByYear W32076582032022 @default.
- W3207658203 countsByYear W32076582032023 @default.
- W3207658203 crossrefType "proceedings-article" @default.
- W3207658203 hasAuthorship W3207658203A5030769176 @default.
- W3207658203 hasAuthorship W3207658203A5063066022 @default.
- W3207658203 hasAuthorship W3207658203A5089409762 @default.
- W3207658203 hasBestOaLocation W32076582032 @default.
- W3207658203 hasConcept C110384440 @default.
- W3207658203 hasConcept C115961682 @default.
- W3207658203 hasConcept C131979681 @default.
- W3207658203 hasConcept C146849305 @default.
- W3207658203 hasConcept C154945302 @default.
- W3207658203 hasConcept C205711294 @default.
- W3207658203 hasConcept C31972630 @default.
- W3207658203 hasConcept C41008148 @default.
- W3207658203 hasConceptScore W3207658203C110384440 @default.
- W3207658203 hasConceptScore W3207658203C115961682 @default.
- W3207658203 hasConceptScore W3207658203C131979681 @default.
- W3207658203 hasConceptScore W3207658203C146849305 @default.
- W3207658203 hasConceptScore W3207658203C154945302 @default.
- W3207658203 hasConceptScore W3207658203C205711294 @default.
- W3207658203 hasConceptScore W3207658203C31972630 @default.
- W3207658203 hasConceptScore W3207658203C41008148 @default.
- W3207658203 hasLocation W32076582031 @default.
- W3207658203 hasLocation W32076582032 @default.
- W3207658203 hasOpenAccess W3207658203 @default.
- W3207658203 hasPrimaryLocation W32076582031 @default.
- W3207658203 hasRelatedWork W1503414886 @default.
- W3207658203 hasRelatedWork W1632903234 @default.
- W3207658203 hasRelatedWork W1863533157 @default.
- W3207658203 hasRelatedWork W2048402902 @default.
- W3207658203 hasRelatedWork W2740010476 @default.
- W3207658203 hasRelatedWork W2979718872 @default.
- W3207658203 hasRelatedWork W3158534694 @default.
- W3207658203 hasRelatedWork W3206828132 @default.
- W3207658203 hasRelatedWork W4290774832 @default.
- W3207658203 hasRelatedWork W3182299699 @default.
- W3207658203 isParatext "false" @default.
- W3207658203 isRetracted "false" @default.
- W3207658203 magId "3207658203" @default.
- W3207658203 workType "article" @default.