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 understanding of indoor 3D point cloud data is crucial for arange of subsequent applications, including indoor service robots, navigationsystems, and digital twin engineering. Global features are crucial forachieving high-quality semantic and instance segmentation of indoor pointclouds, as they provide essential long-range context information. To this end,we propose JSMNet, which combines a multi-layer network with a global featureself-attention module to jointly segment three-dimensional point cloudsemantics and instances. To better express the characteristics of indoortargets, we have designed a multi-resolution feature adaptive fusion modulethat takes into account the differences in point cloud density caused byvarying scanner distances from the target. Additionally, we propose a frameworkfor joint semantic and instance segmentation by integrating semantic andinstance features to achieve superior results. We conduct experiments on S3DIS,which is a large three-dimensional indoor point cloud dataset. Our proposedmethod is compared against other methods, and the results show that itoutperforms existing methods in semantic and instance segmentation and providesbetter results in target local area segmentation. Specifically, our proposedmethod outperforms PointNet (Qi et al., 2017a) by 16.0% and 26.3% in terms ofsemantic segmentation mIoU in S3DIS (Area 5) and instance segmentation mPre,respectively. Additionally, it surpasses ASIS (Wang et al., 2019) by 6.0% and4.6%, respectively, as well as JSPNet (Chen et al., 2022) by a margin of 3.3%for semantic segmentation mIoU and a slight improvement of 0.3% for instancesegmentation mPre.

JSMNet Improving Indoor Point Cloud Semantic and Instance Segmentation through Self-Attention and Multiscale