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

This paper investigates the indistinguishable points (difficult to predictlabel) in semantic segmentation for large-scale 3D point clouds. Theindistinguishable points consist of those located in complex boundary, pointswith similar local textures but different categories, and points in isolatesmall hard areas, which largely harm the performance of 3D semanticsegmentation. To address this challenge, we propose a novel IndistinguishableArea Focalization Network (IAF-Net), which selects indistinguishable pointsadaptively by utilizing the hierarchical semantic features and enhancesfine-grained features for points especially those indistinguishable points. Wealso introduce multi-stage loss to improve the feature representation in aprogressive way. Moreover, in order to analyze the segmentation performances ofindistinguishable areas, we propose a new evaluation metric calledIndistinguishable Points Based Metric (IPBM). Our IAF-Net achieves thecomparable results with state-of-the-art performance on several popular 3Dpoint cloud datasets e.g. S3DIS and ScanNet, and clearly outperforms othermethods on IPBM.

Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud