Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226380478> ?p ?o ?g. }
- W4226380478 endingPage "5849" @default.
- W4226380478 startingPage "5842" @default.
- W4226380478 abstract "Building point-to-point dense correspondence between non-rigid shapes is a fundamental and challenging problem. Although functional map-based methods which calculate basis and convert point-wise map to functional map have shown promising performance on meshes, they are not directly applicable to point clouds. Recently, learning-based frameworks were proposed to estimate correspondence directly using extracted features from non-rigid shapes, but they could not handle serious deformation well, especially with highly symmetrical and distorted shapes. In this letter, we propose a deep graph matching based end-to-end learning framework for building dense correspondence between non-rigid point clouds. Unlike functional map-based methods or recent learning-based studies, here we formulate correspondence estimation as a graph matching problem and use deep graph matching to better utilize both local geometry and global structure information. Specifically, we propose a Graph Generator, which takes high-dimensional features as nodes and calculates point-wise Euclidean distance as edges to build graphs. After the graphs’ topological structure information is embedded into nodes by the Graph Embedding Layer, the Affinity Layer and Sinkhorn Layer are used to estimate correspondence matrix between two point clouds finally. Extensive experiments on both synthetic and real scanned datasets show that the proposed method not only achieves better quantitative and qualitative performance, but also has better generalization than existing methods." @default.
- W4226380478 created "2022-05-05" @default.
- W4226380478 creator A5007027174 @default.
- W4226380478 creator A5011879942 @default.
- W4226380478 creator A5029371371 @default.
- W4226380478 creator A5035262213 @default.
- W4226380478 creator A5091832670 @default.
- W4226380478 date "2022-07-01" @default.
- W4226380478 modified "2023-09-26" @default.
- W4226380478 title "Deep Graph Matching Based Dense Correspondence Learning Between Non-Rigid Point Clouds" @default.
- W4226380478 cites W1985907520 @default.
- W4226380478 cites W1990283121 @default.
- W4226380478 cites W1992397549 @default.
- W4226380478 cites W2013603106 @default.
- W4226380478 cites W2047161559 @default.
- W4226380478 cites W2049981393 @default.
- W4226380478 cites W2110026675 @default.
- W4226380478 cites W2141461755 @default.
- W4226380478 cites W2166820607 @default.
- W4226380478 cites W2168722300 @default.
- W4226380478 cites W2172062571 @default.
- W4226380478 cites W2696471905 @default.
- W4226380478 cites W2737081152 @default.
- W4226380478 cites W2811184427 @default.
- W4226380478 cites W2859599500 @default.
- W4226380478 cites W2883758202 @default.
- W4226380478 cites W2962771259 @default.
- W4226380478 cites W2962934458 @default.
- W4226380478 cites W2963242400 @default.
- W4226380478 cites W2969150231 @default.
- W4226380478 cites W2975149757 @default.
- W4226380478 cites W2979750740 @default.
- W4226380478 cites W2983178467 @default.
- W4226380478 cites W2986382673 @default.
- W4226380478 cites W2990613095 @default.
- W4226380478 cites W3004808484 @default.
- W4226380478 cites W3008681115 @default.
- W4226380478 cites W3034883642 @default.
- W4226380478 cites W3035612424 @default.
- W4226380478 cites W3039448353 @default.
- W4226380478 cites W3092669602 @default.
- W4226380478 cites W3106189303 @default.
- W4226380478 cites W3129618687 @default.
- W4226380478 cites W3166285241 @default.
- W4226380478 cites W3166855724 @default.
- W4226380478 cites W3168920280 @default.
- W4226380478 cites W3170435764 @default.
- W4226380478 cites W3172793249 @default.
- W4226380478 cites W3181191249 @default.
- W4226380478 cites W3195006234 @default.
- W4226380478 cites W4210257598 @default.
- W4226380478 cites W4243293508 @default.
- W4226380478 doi "https://doi.org/10.1109/lra.2022.3160237" @default.
- W4226380478 hasPublicationYear "2022" @default.
- W4226380478 type Work @default.
- W4226380478 citedByCount "2" @default.
- W4226380478 countsByYear W42263804782022 @default.
- W4226380478 countsByYear W42263804782023 @default.
- W4226380478 crossrefType "journal-article" @default.
- W4226380478 hasAuthorship W4226380478A5007027174 @default.
- W4226380478 hasAuthorship W4226380478A5011879942 @default.
- W4226380478 hasAuthorship W4226380478A5029371371 @default.
- W4226380478 hasAuthorship W4226380478A5035262213 @default.
- W4226380478 hasAuthorship W4226380478A5091832670 @default.
- W4226380478 hasConcept C105795698 @default.
- W4226380478 hasConcept C11413529 @default.
- W4226380478 hasConcept C129782007 @default.
- W4226380478 hasConcept C131979681 @default.
- W4226380478 hasConcept C132525143 @default.
- W4226380478 hasConcept C134306372 @default.
- W4226380478 hasConcept C153180895 @default.
- W4226380478 hasConcept C154945302 @default.
- W4226380478 hasConcept C165064840 @default.
- W4226380478 hasConcept C177148314 @default.
- W4226380478 hasConcept C200336642 @default.
- W4226380478 hasConcept C2524010 @default.
- W4226380478 hasConcept C28719098 @default.
- W4226380478 hasConcept C33923547 @default.
- W4226380478 hasConcept C41008148 @default.
- W4226380478 hasConcept C41608201 @default.
- W4226380478 hasConcept C80444323 @default.
- W4226380478 hasConceptScore W4226380478C105795698 @default.
- W4226380478 hasConceptScore W4226380478C11413529 @default.
- W4226380478 hasConceptScore W4226380478C129782007 @default.
- W4226380478 hasConceptScore W4226380478C131979681 @default.
- W4226380478 hasConceptScore W4226380478C132525143 @default.
- W4226380478 hasConceptScore W4226380478C134306372 @default.
- W4226380478 hasConceptScore W4226380478C153180895 @default.
- W4226380478 hasConceptScore W4226380478C154945302 @default.
- W4226380478 hasConceptScore W4226380478C165064840 @default.
- W4226380478 hasConceptScore W4226380478C177148314 @default.
- W4226380478 hasConceptScore W4226380478C200336642 @default.
- W4226380478 hasConceptScore W4226380478C2524010 @default.
- W4226380478 hasConceptScore W4226380478C28719098 @default.
- W4226380478 hasConceptScore W4226380478C33923547 @default.
- W4226380478 hasConceptScore W4226380478C41008148 @default.
- W4226380478 hasConceptScore W4226380478C41608201 @default.
- W4226380478 hasConceptScore W4226380478C80444323 @default.