FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2974621909> ?p ?o ?g. }

• W2974621909 abstract "We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid CNN kernels, the spherical kernel maintains translation-invariance and asymmetry properties, where the former guarantees weight sharing among similar local structures in the data and the latter facilitates fine geometric learning. The proposed kernel is applied to graph neural networks without edge-dependent filter generation, making it computationally attractive for large point clouds. In our graph networks, each vertex is associated with a single point location and edges connect the neighborhood points within a defined range. The graph gets coarsened in the network with farthest point sampling. Analogous to the standard CNNs, we define pooling and unpooling operations for our network. We demonstrate the effectiveness of the proposed spherical kernel with graph neural networks for point cloud classification and semantic segmentation using ModelNet, ShapeNet, RueMonge2014, ScanNet and S3DIS datasets. The source code and the trained models can be downloaded from https://github.com/hlei-ziyan/SPH3D-GCN." @default.
• W2974621909 created "2019-09-26" @default.
• W2974621909 creator A5034919276 @default.
• W2974621909 creator A5036476165 @default.
• W2974621909 creator A5069697936 @default.
• W2974621909 date "2019-09-19" @default.
• W2974621909 modified "2023-09-23" @default.
• W2974621909 title "Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds" @default.
• W2974621909 cites W1501856433 @default.
• W2974621909 cites W1564871316 @default.
• W2974621909 cites W1819285909 @default.
• W2974621909 cites W1836465849 @default.
• W2974621909 cites W1901129140 @default.
• W2974621909 cites W1903029394 @default.
• W2974621909 cites W1903208982 @default.
• W2974621909 cites W1920022804 @default.
• W2974621909 cites W1963882359 @default.
• W2974621909 cites W2005314985 @default.
• W2974621909 cites W2057175746 @default.
• W2974621909 cites W2077251165 @default.
• W2974621909 cites W2095705004 @default.
• W2974621909 cites W2097117768 @default.
• W2974621909 cites W2112796928 @default.
• W2974621909 cites W2116341502 @default.
• W2974621909 cites W2133098875 @default.
• W2974621909 cites W2147880316 @default.
• W2974621909 cites W2151103935 @default.
• W2974621909 cites W2152864241 @default.
• W2974621909 cites W2160643963 @default.
• W2974621909 cites W2161969291 @default.
• W2974621909 cites W2163605009 @default.
• W2974621909 cites W2190691619 @default.
• W2974621909 cites W2194775991 @default.
• W2974621909 cites W2211722331 @default.
• W2974621909 cites W2402144811 @default.
• W2974621909 cites W2414711238 @default.
• W2974621909 cites W2460657278 @default.
• W2974621909 cites W250737475 @default.
• W2974621909 cites W2531409750 @default.
• W2974621909 cites W2553307952 @default.
• W2974621909 cites W2556802233 @default.
• W2974621909 cites W2558748708 @default.
• W2974621909 cites W2560609797 @default.
• W2974621909 cites W2566265240 @default.
• W2974621909 cites W2594519801 @default.
• W2974621909 cites W2606202972 @default.
• W2974621909 cites W2609719703 @default.
• W2974621909 cites W2613718673 @default.
• W2974621909 cites W2624273542 @default.
• W2974621909 cites W2768308213 @default.
• W2974621909 cites W2785053089 @default.
• W2974621909 cites W2788158258 @default.
• W2974621909 cites W2795374598 @default.
• W2974621909 cites W2797997528 @default.
• W2974621909 cites W2798270772 @default.
• W2974621909 cites W2895472109 @default.
• W2974621909 cites W2902302021 @default.
• W2974621909 cites W2948107928 @default.
• W2974621909 cites W2950493473 @default.
• W2974621909 cites W2950898568 @default.
• W2974621909 cites W2953399169 @default.
• W2974621909 cites W2955873422 @default.
• W2974621909 cites W2962751169 @default.
• W2974621909 cites W2962835968 @default.
• W2974621909 cites W2962928871 @default.
• W2974621909 cites W2963037989 @default.
• W2974621909 cites W2963053547 @default.
• W2974621909 cites W2963094037 @default.
• W2974621909 cites W2963121255 @default.
• W2974621909 cites W2963125977 @default.
• W2974621909 cites W2963158438 @default.
• W2974621909 cites W2963182550 @default.
• W2974621909 cites W2963226018 @default.
• W2974621909 cites W2963231572 @default.
• W2974621909 cites W2963281829 @default.
• W2974621909 cites W2963333168 @default.
• W2974621909 cites W2963632978 @default.
• W2974621909 cites W2963706542 @default.
• W2974621909 cites W2963719584 @default.
• W2974621909 cites W2963721253 @default.
• W2974621909 cites W2963881378 @default.
• W2974621909 cites W2964015378 @default.
• W2974621909 cites W2964017310 @default.
• W2974621909 cites W2964027736 @default.
• W2974621909 cites W2964121744 @default.
• W2974621909 cites W2964253930 @default.
• W2974621909 cites W2964311892 @default.
• W2974621909 cites W2964321699 @default.
• W2974621909 cites W2981199548 @default.
• W2974621909 cites W2990613095 @default.
• W2974621909 cites W3103830808 @default.
• W2974621909 cites W3106250896 @default.
• W2974621909 cites W3122633743 @default.
• W2974621909 cites W603908379 @default.
• W2974621909 cites W764651262 @default.
• W2974621909 doi "https://doi.org/10.48550/arxiv.1909.09287" @default.
• W2974621909 hasPublicationYear "2019" @default.
• W2974621909 type Work @default.
• W2974621909 sameAs 2974621909 @default.
• W2974621909 citedByCount "5" @default.

• next