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

Large-scale semantic mapping is crucial for outdoor autonomous agents tofulfill high-level tasks such as planning and navigation. This paper proposes anovel method for large-scale 3D semantic reconstruction through implicitrepresentations from LiDAR measurements alone. We firstly leverages anoctree-based and hierarchical structure to store implicit features, then theseimplicit features are decoded to semantic information and signed distance valuethrough shallow Multilayer Perceptrons (MLPs). We adopt off-the-shelfalgorithms to predict the semantic labels and instance IDs of point cloud. Thenwe jointly optimize the implicit features and MLPs parameters withself-supervision paradigm for point cloud geometry and pseudo-supervisionpradigm for semantic and panoptic labels. Subsequently, Marching Cubesalgorithm is exploited to subdivide and visualize the scenes in the inferringstage. For scenarios with memory constraints, a map stitching strategy is alsodeveloped to merge sub-maps into a complete map. As far as we know, our methodis the first work to reconstruct semantic implicit scenes from LiDAR-onlyinput. Experiments on three real-world datasets, SemanticKITTI, SemanticPOSSand nuScenes, demonstrate the effectiveness and efficiency of our frameworkcompared to current state-of-the-art 3D mapping methods.

LISNeRF Mapping: LiDAR-based Implicit Mapping via Semantic Neural Fields for Large-Scale 3D Scenes