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 mapping is important yet challenging in self-driving and mobilerobotics. To tackle such a global point cloud registration problem, DeepMappingconverts the complex map estimation into a self-supervised training of simpledeep networks. Despite its broad convergence range on small datasets,DeepMapping still cannot produce satisfactory results on large-scale datasetswith thousands of frames. This is due to the lack of loop closures and exactcross-frame point correspondences, and the slow convergence of its globallocalization network. We propose DeepMapping2 by adding two novel techniques toaddress these issues: (1) organization of training batch based on map topologyfrom loop closing, and (2) self-supervised local-to-global point consistencyloss leveraging pairwise registration. Our experiments and ablation studies onpublic datasets (KITTI, NCLT, and Nebula) demonstrate the effectiveness of ourmethod.

DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization