Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376481231> ?p ?o ?g. }
Showing items 1 to 52 of
52
with 100 items per page.
- W4376481231 endingPage "1" @default.
- W4376481231 startingPage "1" @default.
- W4376481231 abstract "Establishing reliable correspondences between two images is a fundamental and important task in computer vision. This paper proposes a novel network called Sparse Graph Attention Network (SGA-Net), to capture rich contextual information of sparse graphs for feature matching task. Specifically, a graph attention block is proposed to enhance the representational ability of graph-structured features. The proposed block introduces a novel normalization technique for graph-structured features to embed global information into each edge feature, and it adopts the squeeze-and-excitation mechanism to capture graph-wise contextual information. Meanwhile, to further obtain interesting structural information of sparse graphs, a novel sparse graph transformer is developed based on multi-headed self-attention mechanism, while maintaining permutation-equivariance. Additionally, considering that the graph contexts in shallow layers are not fully exploited, a simple graph-context fusion block is introduced to adaptively capture topological information from different layers by implicitly modeling the interdependence between these graph contexts. The proposed SGA-Net can search dependable candidates among the putative correspondences and simultaneously estimate accurate camera poses for two-view geometry estimation. Extensive experiments on outlier removal and camera pose estimation tasks have demonstrated that the proposed SGA-Net outperforms state-of-the-art methods on both outdoor and indoor benchmarks (i.e., YFCC100M and SUN3D). SGA-Net achieves a mAP5° of 58.88% without RANSAC on the outdoor dataset, and it achieves a precision increase of 13.45% and 7.34% compared with the state-of-the-art result on outdoor and indoor datasets, respectively." @default.
- W4376481231 created "2023-05-14" @default.
- W4376481231 creator A5020704871 @default.
- W4376481231 creator A5043306089 @default.
- W4376481231 creator A5050524397 @default.
- W4376481231 creator A5068882471 @default.
- W4376481231 creator A5078961342 @default.
- W4376481231 date "2023-01-01" @default.
- W4376481231 modified "2023-10-01" @default.
- W4376481231 title "SGA-Net: A Sparse Graph Attention Network for Two-View Correspondence Learning" @default.
- W4376481231 doi "https://doi.org/10.1109/tcsvt.2023.3275817" @default.
- W4376481231 hasPublicationYear "2023" @default.
- W4376481231 type Work @default.
- W4376481231 citedByCount "0" @default.
- W4376481231 crossrefType "journal-article" @default.
- W4376481231 hasAuthorship W4376481231A5020704871 @default.
- W4376481231 hasAuthorship W4376481231A5043306089 @default.
- W4376481231 hasAuthorship W4376481231A5050524397 @default.
- W4376481231 hasAuthorship W4376481231A5068882471 @default.
- W4376481231 hasAuthorship W4376481231A5078961342 @default.
- W4376481231 hasConcept C132525143 @default.
- W4376481231 hasConcept C153180895 @default.
- W4376481231 hasConcept C154945302 @default.
- W4376481231 hasConcept C2993807640 @default.
- W4376481231 hasConcept C41008148 @default.
- W4376481231 hasConcept C79337645 @default.
- W4376481231 hasConcept C80444323 @default.
- W4376481231 hasConceptScore W4376481231C132525143 @default.
- W4376481231 hasConceptScore W4376481231C153180895 @default.
- W4376481231 hasConceptScore W4376481231C154945302 @default.
- W4376481231 hasConceptScore W4376481231C2993807640 @default.
- W4376481231 hasConceptScore W4376481231C41008148 @default.
- W4376481231 hasConceptScore W4376481231C79337645 @default.
- W4376481231 hasConceptScore W4376481231C80444323 @default.
- W4376481231 hasLocation W43764812311 @default.
- W4376481231 hasOpenAccess W4376481231 @default.
- W4376481231 hasPrimaryLocation W43764812311 @default.
- W4376481231 hasRelatedWork W2033914206 @default.
- W4376481231 hasRelatedWork W2046077695 @default.
- W4376481231 hasRelatedWork W2146076056 @default.
- W4376481231 hasRelatedWork W2163831990 @default.
- W4376481231 hasRelatedWork W3003836766 @default.
- W4376481231 hasRelatedWork W3088227725 @default.
- W4376481231 hasRelatedWork W3107474891 @default.
- W4376481231 hasRelatedWork W4285102013 @default.
- W4376481231 hasRelatedWork W4307640250 @default.
- W4376481231 hasRelatedWork W4312323421 @default.
- W4376481231 isParatext "false" @default.
- W4376481231 isRetracted "false" @default.
- W4376481231 workType "article" @default.