Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897855555> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W2897855555 abstract "This research is concerned with semantic segmentation of 3D point clouds arising from videos of 3D indoor scenes. It is an important building block of 3D scene understanding and has promising applications such as augmented reality and robotics. Although various deep learning based approaches have been proposed to replicate the success of 2D semantic segmentation in 3D domain, they either result in severe information loss or fail to model the geometric structures well. In this paper, we aim to model the local and global geometric structures of 3D scenes by designing an end-to-end 3D semantic segmentation framework. It captures the local geometries from point-level feature learning and voxel-level aggregation, models the global structures via 3D CNN, and enforces label consistency with high-order CRF. Through preliminary experiments conducted on two indoor datasets, we describe our insights on the proposed approach, and present some directions to be pursued in the future." @default.
- W2897855555 created "2018-10-26" @default.
- W2897855555 creator A5071387519 @default.
- W2897855555 date "2018-10-15" @default.
- W2897855555 modified "2023-09-24" @default.
- W2897855555 title "End2End Semantic Segmentation for 3D Indoor Scenes" @default.
- W2897855555 cites W1629010235 @default.
- W2897855555 cites W1644641054 @default.
- W2897855555 cites W1903029394 @default.
- W2897855555 cites W2063855692 @default.
- W2897855555 cites W2086225343 @default.
- W2897855555 cites W2095389390 @default.
- W2897855555 cites W2124592697 @default.
- W2897855555 cites W2210040239 @default.
- W2897855555 cites W2340897893 @default.
- W2897855555 cites W2460657278 @default.
- W2897855555 cites W2518780089 @default.
- W2897855555 cites W2556802233 @default.
- W2897855555 cites W2594519801 @default.
- W2897855555 cites W2614059183 @default.
- W2897855555 cites W2963753570 @default.
- W2897855555 cites W3103830808 @default.
- W2897855555 doi "https://doi.org/10.1145/3240508.3243933" @default.
- W2897855555 hasPublicationYear "2018" @default.
- W2897855555 type Work @default.
- W2897855555 sameAs 2897855555 @default.
- W2897855555 citedByCount "5" @default.
- W2897855555 countsByYear W28978555552020 @default.
- W2897855555 countsByYear W28978555552021 @default.
- W2897855555 countsByYear W28978555552022 @default.
- W2897855555 crossrefType "proceedings-article" @default.
- W2897855555 hasAuthorship W2897855555A5071387519 @default.
- W2897855555 hasConcept C124504099 @default.
- W2897855555 hasConcept C154945302 @default.
- W2897855555 hasConcept C31972630 @default.
- W2897855555 hasConcept C41008148 @default.
- W2897855555 hasConcept C89600930 @default.
- W2897855555 hasConceptScore W2897855555C124504099 @default.
- W2897855555 hasConceptScore W2897855555C154945302 @default.
- W2897855555 hasConceptScore W2897855555C31972630 @default.
- W2897855555 hasConceptScore W2897855555C41008148 @default.
- W2897855555 hasConceptScore W2897855555C89600930 @default.
- W2897855555 hasLocation W28978555551 @default.
- W2897855555 hasOpenAccess W2897855555 @default.
- W2897855555 hasPrimaryLocation W28978555551 @default.
- W2897855555 hasRelatedWork W1507266234 @default.
- W2897855555 hasRelatedWork W1669643531 @default.
- W2897855555 hasRelatedWork W1700740617 @default.
- W2897855555 hasRelatedWork W1721780360 @default.
- W2897855555 hasRelatedWork W2110230079 @default.
- W2897855555 hasRelatedWork W2117664411 @default.
- W2897855555 hasRelatedWork W2117933325 @default.
- W2897855555 hasRelatedWork W2122581818 @default.
- W2897855555 hasRelatedWork W2159066190 @default.
- W2897855555 hasRelatedWork W2739874619 @default.
- W2897855555 isParatext "false" @default.
- W2897855555 isRetracted "false" @default.
- W2897855555 magId "2897855555" @default.
- W2897855555 workType "article" @default.