English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semantic segmentation of point clouds generates comprehensive understandingof scenes through densely predicting the category for each point. Due to theunicity of receptive field, semantic segmentation of point clouds remainschallenging for the expression of multi-receptive field features, which bringsabout the misclassification of instances with similar spatial structures. Inthis paper, we propose a graph convolutional network DGFA-Net rooted in dilatedgraph feature aggregation (DGFA), guided by multi-basis aggregation loss(MALoss) calculated through Pyramid Decoders. To configure multi-receptivefield features, DGFA which takes the proposed dilated graph convolution(DGConv) as its basic building block, is designed to aggregate multi-scalefeature representation by capturing dilated graphs with various receptiveregions. By simultaneously considering penalizing the receptive fieldinformation with point sets of different resolutions as calculation bases, weintroduce Pyramid Decoders driven by MALoss for the diversity of receptivefield bases. Combining these two aspects, DGFA-Net significantly improves thesegmentation performance of instances with similar spatial structures.Experiments on S3DIS, ShapeNetPart and Toronto-3D show that DGFA-Netoutperforms the baseline approach, achieving a new state-of-the-artsegmentation performance.

Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders