Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377041966> ?p ?o ?g. }
- W4377041966 endingPage "6098" @default.
- W4377041966 startingPage "6098" @default.
- W4377041966 abstract "Currently, 3D objects are usually represented by 3D bounding boxes. Much research work has focused on detecting 3D objects directly from point clouds, and significant progress has been made in this field. However, we find there are there is still room for improvement in three aspects. First is point cloud feature extraction. Many successful methods are based on PointNet/PointNet++, which uses multi-layer perceptrons (MLP) to extract features to generate seed points, without considering foreground and background clues. The second aspect is grouping. The “vote-based cluster” grouping method defined by the pioneering VoteNet ignores shape information that is very important in the object detection field. The final aspect is the modeling ability of grouped clusters. Most successful methods treat grouped clusters separately, regardless of their different contributions to the final detection. To address these challenges, we propose three modules to address them: the foreground-aware module, the voting-aware module, and the cluster-aware module. Extensive experiments on two large datasets of real 3D scans, ScanNet and SUN RGB-D, demonstrate the effectiveness of our method for 3D object detection on point clouds." @default.
- W4377041966 created "2023-05-19" @default.
- W4377041966 creator A5000669556 @default.
- W4377041966 creator A5054137460 @default.
- W4377041966 creator A5062337989 @default.
- W4377041966 creator A5076386446 @default.
- W4377041966 creator A5091863867 @default.
- W4377041966 creator A5091974960 @default.
- W4377041966 date "2023-05-16" @default.
- W4377041966 modified "2023-10-17" @default.
- W4377041966 title "REGNet: Ray-Based Enhancement Grouping for 3D Object Detection Based on Point Cloud" @default.
- W4377041966 cites W2122122381 @default.
- W4377041966 cites W2555618208 @default.
- W4377041966 cites W2560722161 @default.
- W4377041966 cites W2603429625 @default.
- W4377041966 cites W2780829839 @default.
- W4377041966 cites W2788158258 @default.
- W4377041966 cites W2797997528 @default.
- W4377041966 cites W2798270772 @default.
- W4377041966 cites W2904332125 @default.
- W4377041966 cites W2905173465 @default.
- W4377041966 cites W2962887844 @default.
- W4377041966 cites W2962928871 @default.
- W4377041966 cites W2963091558 @default.
- W4377041966 cites W2963094037 @default.
- W4377041966 cites W2963150697 @default.
- W4377041966 cites W2963400571 @default.
- W4377041966 cites W2963727135 @default.
- W4377041966 cites W2964062501 @default.
- W4377041966 cites W2964253930 @default.
- W4377041966 cites W2964266557 @default.
- W4377041966 cites W2968296999 @default.
- W4377041966 cites W3003639745 @default.
- W4377041966 cites W3027732325 @default.
- W4377041966 cites W3034317268 @default.
- W4377041966 cites W3034428269 @default.
- W4377041966 cites W3034429258 @default.
- W4377041966 cites W3034579518 @default.
- W4377041966 cites W3034584726 @default.
- W4377041966 cites W3034664537 @default.
- W4377041966 cites W3035057392 @default.
- W4377041966 cites W3035346742 @default.
- W4377041966 cites W3035709245 @default.
- W4377041966 cites W3096387236 @default.
- W4377041966 cites W3096754345 @default.
- W4377041966 cites W3107400217 @default.
- W4377041966 cites W3109395584 @default.
- W4377041966 cites W3113876851 @default.
- W4377041966 cites W3117804044 @default.
- W4377041966 cites W3166470370 @default.
- W4377041966 cites W3183392001 @default.
- W4377041966 cites W4206434639 @default.
- W4377041966 cites W4214526701 @default.
- W4377041966 cites W4214624153 @default.
- W4377041966 cites W4214704706 @default.
- W4377041966 cites W4226344270 @default.
- W4377041966 cites W4308236021 @default.
- W4377041966 cites W4313136902 @default.
- W4377041966 doi "https://doi.org/10.3390/app13106098" @default.
- W4377041966 hasPublicationYear "2023" @default.
- W4377041966 type Work @default.
- W4377041966 citedByCount "0" @default.
- W4377041966 crossrefType "journal-article" @default.
- W4377041966 hasAuthorship W4377041966A5000669556 @default.
- W4377041966 hasAuthorship W4377041966A5054137460 @default.
- W4377041966 hasAuthorship W4377041966A5062337989 @default.
- W4377041966 hasAuthorship W4377041966A5076386446 @default.
- W4377041966 hasAuthorship W4377041966A5091863867 @default.
- W4377041966 hasAuthorship W4377041966A5091974960 @default.
- W4377041966 hasBestOaLocation W43770419661 @default.
- W4377041966 hasConcept C131979681 @default.
- W4377041966 hasConcept C138885662 @default.
- W4377041966 hasConcept C153180895 @default.
- W4377041966 hasConcept C154945302 @default.
- W4377041966 hasConcept C202444582 @default.
- W4377041966 hasConcept C2524010 @default.
- W4377041966 hasConcept C2776151529 @default.
- W4377041966 hasConcept C2776401178 @default.
- W4377041966 hasConcept C2781238097 @default.
- W4377041966 hasConcept C28719098 @default.
- W4377041966 hasConcept C31972630 @default.
- W4377041966 hasConcept C33923547 @default.
- W4377041966 hasConcept C41008148 @default.
- W4377041966 hasConcept C41895202 @default.
- W4377041966 hasConcept C9652623 @default.
- W4377041966 hasConceptScore W4377041966C131979681 @default.
- W4377041966 hasConceptScore W4377041966C138885662 @default.
- W4377041966 hasConceptScore W4377041966C153180895 @default.
- W4377041966 hasConceptScore W4377041966C154945302 @default.
- W4377041966 hasConceptScore W4377041966C202444582 @default.
- W4377041966 hasConceptScore W4377041966C2524010 @default.
- W4377041966 hasConceptScore W4377041966C2776151529 @default.
- W4377041966 hasConceptScore W4377041966C2776401178 @default.
- W4377041966 hasConceptScore W4377041966C2781238097 @default.
- W4377041966 hasConceptScore W4377041966C28719098 @default.
- W4377041966 hasConceptScore W4377041966C31972630 @default.
- W4377041966 hasConceptScore W4377041966C33923547 @default.
- W4377041966 hasConceptScore W4377041966C41008148 @default.