Matches in SemOpenAlex for { <https://semopenalex.org/work/W4245917595> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4245917595 abstract "Point cloud registration is a fundamental but important technique in robotics and computer vision, such as 3D reconstruction, simultaneous localization and mapping (SLAM). The classical methods used hand-craft features extracted from each point cloud to estimate the rigid transformation between point clouds with iterative closest points (ICP) or its variants. Recently, deep learning has been widely used in object detection, segmentation and registration, especially the well-known work, PointNet, changed how we think about the representation of point clouds. However, the local information is ignored in PointNet as many works pointed out. In this paper, we advise to use graph attention to aggregate local features and a kind of cross attention method for point cloud registration. Firstly, we use a mini-ConvNet to extract point-wise features for sampled points and their neighbors. Then graph attention is applied to aggregate the local information from neighbor points to center points. We consider that previous works which directly estimate the transformation using the features from two point clouds ignore some relationship between the point clouds. Instead, we propose to explore the relation with a kind of cross attention. We perform extensive experiments to validate the effectiveness of our method." @default.
- W4245917595 created "2022-05-12" @default.
- W4245917595 creator A5031976013 @default.
- W4245917595 creator A5046775442 @default.
- W4245917595 creator A5069188763 @default.
- W4245917595 date "2021-10-22" @default.
- W4245917595 modified "2023-09-24" @default.
- W4245917595 title "Graph Attention based Point Cloud Registration" @default.
- W4245917595 doi "https://doi.org/10.1109/cac53003.2021.9727337" @default.
- W4245917595 hasPublicationYear "2021" @default.
- W4245917595 type Work @default.
- W4245917595 citedByCount "0" @default.
- W4245917595 crossrefType "proceedings-article" @default.
- W4245917595 hasAuthorship W4245917595A5031976013 @default.
- W4245917595 hasAuthorship W4245917595A5046775442 @default.
- W4245917595 hasAuthorship W4245917595A5069188763 @default.
- W4245917595 hasConcept C104317684 @default.
- W4245917595 hasConcept C126795593 @default.
- W4245917595 hasConcept C131979681 @default.
- W4245917595 hasConcept C132525143 @default.
- W4245917595 hasConcept C154945302 @default.
- W4245917595 hasConcept C185592680 @default.
- W4245917595 hasConcept C195958017 @default.
- W4245917595 hasConcept C19966478 @default.
- W4245917595 hasConcept C204241405 @default.
- W4245917595 hasConcept C2524010 @default.
- W4245917595 hasConcept C28719098 @default.
- W4245917595 hasConcept C31972630 @default.
- W4245917595 hasConcept C33923547 @default.
- W4245917595 hasConcept C41008148 @default.
- W4245917595 hasConcept C55493867 @default.
- W4245917595 hasConcept C80444323 @default.
- W4245917595 hasConcept C86369673 @default.
- W4245917595 hasConcept C89600930 @default.
- W4245917595 hasConcept C90509273 @default.
- W4245917595 hasConceptScore W4245917595C104317684 @default.
- W4245917595 hasConceptScore W4245917595C126795593 @default.
- W4245917595 hasConceptScore W4245917595C131979681 @default.
- W4245917595 hasConceptScore W4245917595C132525143 @default.
- W4245917595 hasConceptScore W4245917595C154945302 @default.
- W4245917595 hasConceptScore W4245917595C185592680 @default.
- W4245917595 hasConceptScore W4245917595C195958017 @default.
- W4245917595 hasConceptScore W4245917595C19966478 @default.
- W4245917595 hasConceptScore W4245917595C204241405 @default.
- W4245917595 hasConceptScore W4245917595C2524010 @default.
- W4245917595 hasConceptScore W4245917595C28719098 @default.
- W4245917595 hasConceptScore W4245917595C31972630 @default.
- W4245917595 hasConceptScore W4245917595C33923547 @default.
- W4245917595 hasConceptScore W4245917595C41008148 @default.
- W4245917595 hasConceptScore W4245917595C55493867 @default.
- W4245917595 hasConceptScore W4245917595C80444323 @default.
- W4245917595 hasConceptScore W4245917595C86369673 @default.
- W4245917595 hasConceptScore W4245917595C89600930 @default.
- W4245917595 hasConceptScore W4245917595C90509273 @default.
- W4245917595 hasLocation W42459175951 @default.
- W4245917595 hasOpenAccess W4245917595 @default.
- W4245917595 hasPrimaryLocation W42459175951 @default.
- W4245917595 hasRelatedWork W125675508 @default.
- W4245917595 hasRelatedWork W2148991343 @default.
- W4245917595 hasRelatedWork W2613626105 @default.
- W4245917595 hasRelatedWork W2807666361 @default.
- W4245917595 hasRelatedWork W2972393937 @default.
- W4245917595 hasRelatedWork W2979718872 @default.
- W4245917595 hasRelatedWork W2991938346 @default.
- W4245917595 hasRelatedWork W3172823523 @default.
- W4245917595 hasRelatedWork W3204162010 @default.
- W4245917595 hasRelatedWork W4321064134 @default.
- W4245917595 isParatext "false" @default.
- W4245917595 isRetracted "false" @default.
- W4245917595 workType "article" @default.