Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313146104> ?p ?o ?g. }
- W4313146104 endingPage "212" @default.
- W4313146104 startingPage "196" @default.
- W4313146104 abstract "In point cloud learning, sparsity and geometry are two core properties. Recently, many approaches have been proposed through single or multiple representations to improve the performance of point cloud semantic segmentation. However, these works fail to maintain the balance among performance, efficiency, and memory consumption, showing incapability to integrate sparsity and geometry appropriately. To address these issues, we propose the Geometry-aware Sparse Networks (GASN) by utilizing the sparsity and geometry of a point cloud in a single voxel representation. GASN mainly consists of two modules, namely Sparse Feature Encoder and Sparse Geometry Feature Enhancement. The Sparse Feature Encoder extracts the local context information, and the Sparse Geometry Feature Enhancement enhances the geometric properties of a sparse point cloud to improve both efficiency and performance. In addition, we propose deep sparse supervision in the training phase to help convergence and alleviate the memory consumption problem. Our GASN achieves state-of-the-art performance on both SemanticKITTI and Nuscenes datasets while running significantly faster and consuming less memory." @default.
- W4313146104 created "2023-01-06" @default.
- W4313146104 creator A5025067700 @default.
- W4313146104 creator A5041668587 @default.
- W4313146104 creator A5058424592 @default.
- W4313146104 creator A5058792328 @default.
- W4313146104 creator A5077950332 @default.
- W4313146104 date "2022-01-01" @default.
- W4313146104 modified "2023-10-14" @default.
- W4313146104 title "Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks" @default.
- W4313146104 cites W1644641054 @default.
- W4313146104 cites W1901129140 @default.
- W4313146104 cites W1903029394 @default.
- W4313146104 cites W2115579991 @default.
- W4313146104 cites W2194775991 @default.
- W4313146104 cites W2211722331 @default.
- W4313146104 cites W2412782625 @default.
- W4313146104 cites W2560023338 @default.
- W4313146104 cites W2752782242 @default.
- W4313146104 cites W2776622059 @default.
- W4313146104 cites W2795587607 @default.
- W4313146104 cites W2797997528 @default.
- W4313146104 cites W2798777114 @default.
- W4313146104 cites W2799213142 @default.
- W4313146104 cites W2890848214 @default.
- W4313146104 cites W2897529137 @default.
- W4313146104 cites W2916798096 @default.
- W4313146104 cites W2922509574 @default.
- W4313146104 cites W2930709109 @default.
- W4313146104 cites W2962912109 @default.
- W4313146104 cites W2963125977 @default.
- W4313146104 cites W2963182550 @default.
- W4313146104 cites W2963231572 @default.
- W4313146104 cites W2963312728 @default.
- W4313146104 cites W2963830382 @default.
- W4313146104 cites W2964266557 @default.
- W4313146104 cites W2979750740 @default.
- W4313146104 cites W2981199548 @default.
- W4313146104 cites W2990613095 @default.
- W4313146104 cites W2991216808 @default.
- W4313146104 cites W3003437478 @default.
- W4313146104 cites W3012494314 @default.
- W4313146104 cites W3035002114 @default.
- W4313146104 cites W3035275207 @default.
- W4313146104 cites W3035574168 @default.
- W4313146104 cites W3043648455 @default.
- W4313146104 cites W3093434340 @default.
- W4313146104 cites W3109154950 @default.
- W4313146104 cites W3109646990 @default.
- W4313146104 cites W3109944402 @default.
- W4313146104 cites W3118723358 @default.
- W4313146104 cites W3137210930 @default.
- W4313146104 cites W3174692508 @default.
- W4313146104 cites W3177330511 @default.
- W4313146104 cites W3181190968 @default.
- W4313146104 cites W3204644301 @default.
- W4313146104 cites W4214755140 @default.
- W4313146104 doi "https://doi.org/10.1007/978-3-031-19842-7_12" @default.
- W4313146104 hasPublicationYear "2022" @default.
- W4313146104 type Work @default.
- W4313146104 citedByCount "1" @default.
- W4313146104 countsByYear W43131461042023 @default.
- W4313146104 crossrefType "book-chapter" @default.
- W4313146104 hasAuthorship W4313146104A5025067700 @default.
- W4313146104 hasAuthorship W4313146104A5041668587 @default.
- W4313146104 hasAuthorship W4313146104A5058424592 @default.
- W4313146104 hasAuthorship W4313146104A5058792328 @default.
- W4313146104 hasAuthorship W4313146104A5077950332 @default.
- W4313146104 hasConcept C124066611 @default.
- W4313146104 hasConcept C131979681 @default.
- W4313146104 hasConcept C138885662 @default.
- W4313146104 hasConcept C151730666 @default.
- W4313146104 hasConcept C153180895 @default.
- W4313146104 hasConcept C154945302 @default.
- W4313146104 hasConcept C2524010 @default.
- W4313146104 hasConcept C2776401178 @default.
- W4313146104 hasConcept C2779343474 @default.
- W4313146104 hasConcept C28719098 @default.
- W4313146104 hasConcept C33923547 @default.
- W4313146104 hasConcept C41008148 @default.
- W4313146104 hasConcept C41895202 @default.
- W4313146104 hasConcept C86803240 @default.
- W4313146104 hasConcept C89600930 @default.
- W4313146104 hasConceptScore W4313146104C124066611 @default.
- W4313146104 hasConceptScore W4313146104C131979681 @default.
- W4313146104 hasConceptScore W4313146104C138885662 @default.
- W4313146104 hasConceptScore W4313146104C151730666 @default.
- W4313146104 hasConceptScore W4313146104C153180895 @default.
- W4313146104 hasConceptScore W4313146104C154945302 @default.
- W4313146104 hasConceptScore W4313146104C2524010 @default.
- W4313146104 hasConceptScore W4313146104C2776401178 @default.
- W4313146104 hasConceptScore W4313146104C2779343474 @default.
- W4313146104 hasConceptScore W4313146104C28719098 @default.
- W4313146104 hasConceptScore W4313146104C33923547 @default.
- W4313146104 hasConceptScore W4313146104C41008148 @default.
- W4313146104 hasConceptScore W4313146104C41895202 @default.
- W4313146104 hasConceptScore W4313146104C86803240 @default.
- W4313146104 hasConceptScore W4313146104C89600930 @default.