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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

LiDAR-based place recognition plays a crucial role in SimultaneousLocalization and Mapping (SLAM) and LiDAR localization.  Despite the emergence of various deep learning-based and hand-crafting-basedmethods, rotation-induced place recognition failure remains a criticalchallenge.  Existing studies address this limitation through specific training strategiesor network structures.  However, the former does not produce satisfactory results, while the latterfocuses mainly on the reduced problem of SO(2) rotation invariance. Methodstargeting SO(3) rotation invariance suffer from limitations in discriminationcapability.  In this paper, we propose a new method that employs Vector Neurons Network(VNN) to achieve SO(3) rotation invariance.  We first extract rotation-equivariant features from neighboring points andmap low-dimensional features to a high-dimensional space through VNN.  Afterwards, we calculate the Euclidean and Cosine distance in therotation-equivariant feature space as rotation-invariant feature descriptors.  Finally, we aggregate the features using GeM pooling to obtain globaldescriptors.  To address the significant information loss when formulatingrotation-invariant descriptors, we propose computing distances between featuresat different layers within the Euclidean space neighborhood.  This greatly improves the discriminability of the point cloud descriptorswhile ensuring computational efficiency.  Experimental results on public datasets show that our approach significantlyoutperforms other baseline methods implementing rotation invariance, whileachieving comparable results with current state-of-the-art place recognitionmethods that do not consider rotation issues.

VNI-Net: Vector Neurons-based Rotation-Invariant Descriptor for LiDAR Place Recognition