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

The semantic segmentation of point clouds is an important part of theenvironment perception for robots. However, it is difficult to directly adoptthe traditional 3D convolution kernel to extract features from raw 3D pointclouds because of the unstructured property of point clouds. In this paper, aspherical interpolated convolution operator is proposed to replace thetraditional grid-shaped 3D convolution operator. This newly proposed featureextraction operator improves the accuracy of the network and reduces theparameters of the network. In addition, this paper analyzes the defect of pointcloud interpolation methods based on the distance as the interpolation weightand proposes the self-learned distance-feature density by combining thedistance and the feature correlation. The proposed method makes the featureextraction of spherical interpolated convolution network more rational andeffective. The effectiveness of the proposed network is demonstrated on the 3Dsemantic segmentation task of point clouds. Experiments show that the proposedmethod achieves good performance on the ScanNet dataset and Paris-Lille-3Ddataset.

Spherical Interpolated Convolutional Network with Distance-Feature Density for 3D Semantic Segmentation of Point Clouds