Matches in SemOpenAlex for { <https://semopenalex.org/work/W2785053089> ?p ?o ?g. }
- W2785053089 abstract "Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. Point clouds inherently lack topological information so designing a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks including ModelNet40, ShapeNetPart, and S3DIS." @default.
- W2785053089 created "2018-02-02" @default.
- W2785053089 creator A5013638126 @default.
- W2785053089 creator A5018812000 @default.
- W2785053089 creator A5019788273 @default.
- W2785053089 creator A5033632697 @default.
- W2785053089 creator A5036542947 @default.
- W2785053089 creator A5056838414 @default.
- W2785053089 date "2018-01-23" @default.
- W2785053089 modified "2023-10-16" @default.
- W2785053089 title "Dynamic Graph CNN for Learning on Point Clouds" @default.
- W2785053089 cites W1596547119 @default.
- W2785053089 cites W1662382123 @default.
- W2785053089 cites W1920022804 @default.
- W2785053089 cites W1951806617 @default.
- W2785053089 cites W1992850481 @default.
- W2785053089 cites W2007200979 @default.
- W2785053089 cites W2007206727 @default.
- W2785053089 cites W2047161559 @default.
- W2785053089 cites W2056108388 @default.
- W2785053089 cites W2072723786 @default.
- W2785053089 cites W2091791686 @default.
- W2785053089 cites W2098764590 @default.
- W2785053089 cites W2099471712 @default.
- W2785053089 cites W2099606917 @default.
- W2785053089 cites W2100657858 @default.
- W2785053089 cites W2101491865 @default.
- W2785053089 cites W2102402541 @default.
- W2785053089 cites W2108444897 @default.
- W2785053089 cites W2116341502 @default.
- W2785053089 cites W2139114878 @default.
- W2785053089 cites W2143357187 @default.
- W2785053089 cites W2147800946 @default.
- W2785053089 cites W2160821342 @default.
- W2785053089 cites W2163605009 @default.
- W2785053089 cites W2165414070 @default.
- W2785053089 cites W2173758409 @default.
- W2785053089 cites W2190691619 @default.
- W2785053089 cites W2203450678 @default.
- W2785053089 cites W2211722331 @default.
- W2785053089 cites W2339077268 @default.
- W2785053089 cites W2460657278 @default.
- W2785053089 cites W2518780089 @default.
- W2785053089 cites W2519887557 @default.
- W2785053089 cites W2553307952 @default.
- W2785053089 cites W2558460151 @default.
- W2785053089 cites W2558748708 @default.
- W2785053089 cites W2560609797 @default.
- W2785053089 cites W2560722161 @default.
- W2785053089 cites W2603429625 @default.
- W2785053089 cites W2606202972 @default.
- W2785053089 cites W2606987267 @default.
- W2785053089 cites W2728183739 @default.
- W2785053089 cites W2737081152 @default.
- W2785053089 cites W2766453196 @default.
- W2785053089 cites W2768308213 @default.
- W2785053089 cites W2769205412 @default.
- W2785053089 cites W2779385920 @default.
- W2785053089 cites W2788158258 @default.
- W2785053089 cites W2796040722 @default.
- W2785053089 cites W2796426482 @default.
- W2785053089 cites W2798895698 @default.
- W2785053089 cites W2894705404 @default.
- W2785053089 cites W2897003273 @default.
- W2785053089 cites W2902302021 @default.
- W2785053089 cites W2903478081 @default.
- W2785053089 cites W2903785932 @default.
- W2785053089 cites W2950898568 @default.
- W2785053089 cites W2951004968 @default.
- W2785053089 cites W2952222609 @default.
- W2785053089 cites W2952254971 @default.
- W2785053089 cites W2952789225 @default.
- W2785053089 cites W2962731536 @default.
- W2785053089 cites W2962865163 @default.
- W2785053089 cites W2962887844 @default.
- W2785053089 cites W2963021451 @default.
- W2785053089 cites W2963043672 @default.
- W2785053089 cites W2963084622 @default.
- W2785053089 cites W2963091558 @default.
- W2785053089 cites W2963121255 @default.
- W2785053089 cites W2963242400 @default.
- W2785053089 cites W2963263347 @default.
- W2785053089 cites W2963333168 @default.
- W2785053089 cites W2963425704 @default.
- W2785053089 cites W2964121744 @default.
- W2785053089 cites W2964253930 @default.
- W2785053089 cites W2964321699 @default.
- W2785053089 cites W3103830808 @default.
- W2785053089 cites W603908379 @default.
- W2785053089 cites W637153065 @default.
- W2785053089 cites W2771185254 @default.
- W2785053089 cites W2787706614 @default.
- W2785053089 doi "https://doi.org/10.48550/arxiv.1801.07829" @default.
- W2785053089 hasPublicationYear "2018" @default.
- W2785053089 type Work @default.
- W2785053089 sameAs 2785053089 @default.
- W2785053089 citedByCount "145" @default.
- W2785053089 countsByYear W27850530892018 @default.
- W2785053089 countsByYear W27850530892019 @default.
- W2785053089 countsByYear W27850530892020 @default.