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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Retrieval-based place recognition is an efficient and effective solution forre-localization within a pre-built map, or global data association forSimultaneous Localization and Mapping (SLAM). The accuracy of such an approachis heavily dependent on the quality of the extracted scene-levelrepresentation. While end-to-end solutions - which learn a global descriptorfrom input point clouds - have demonstrated promising results, such approachesare limited in their ability to enforce desirable properties at the localfeature level. In this paper, we introduce a local consistency loss to guidethe network towards learning local features which are consistent acrossrevisits, hence leading to more repeatable global descriptors resulting in anoverall improvement in 3D place recognition performance. We formulate ourapproach in an end-to-end trainable architecture called LoGG3D-Net. Experimentson two large-scale public benchmarks (KITTI and MulRan) show that our methodachieves mean $F1_{max}$ scores of $0.939$ and $0.968$ on KITTI and MulRanrespectively, achieving state-of-the-art performance while operating in nearreal-time. The open-source implementation is available at:https://github.com/csiro-robotics/LoGG3D-Net.

LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition