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

Besides local features, global information plays an essential role insemantic segmentation, while recent works usually fail to explicitly extractthe meaningful global information and make full use of it. In this paper, wepropose a SceneEncoder module to impose a scene-aware guidance to enhance theeffect of global information. The module predicts a scene descriptor, whichlearns to represent the categories of objects existing in the scene anddirectly guides the point-level semantic segmentation through filtering outcategories not belonging to this scene. Additionally, to alleviate segmentationnoise in local region, we design a region similarity loss to propagatedistinguishing features to their own neighboring points with the same label,leading to the enhancement of the distinguishing ability of point-wisefeatures. We integrate our methods into several prevailing networks and conductextensive experiments on benchmark datasets ScanNet and ShapeNet. Results showthat our methods greatly improve the performance of baselines and achievestate-of-the-art performance.

SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor