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

LIDAR semantic segmentation, which assigns a semantic label to each 3D pointmeasured by the LIDAR, is becoming an essential task for many roboticapplications such as autonomous driving. Fast and efficient semanticsegmentation methods are needed to match the strong computational and temporalrestrictions of many of these real-world applications.  This work presents 3D-MiniNet, a novel approach for LIDAR semanticsegmentation that combines 3D and 2D learning layers. It first learns a 2Drepresentation from the raw points through a novel projection which extractslocal and global information from the 3D data. This representation is fed to anefficient 2D Fully Convolutional Neural Network (FCNN) that produces a 2Dsemantic segmentation. These 2D semantic labels are re-projected back to the 3Dspace and enhanced through a post-processing module. The main novelty in ourstrategy relies on the projection learning module. Our detailed ablation studyshows how each component contributes to the final performance of 3D-MiniNet. Wevalidate our approach on well known public benchmarks (SemanticKITTI andKITTI), where 3D-MiniNet gets state-of-the-art results while being faster andmore parameter-efficient than previous methods.

3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation