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

Extracting robust and general 3D local features is key to downstream taskssuch as point cloud registration and reconstruction. Existing learning-basedlocal descriptors are either sensitive to rotation transformations, or rely onclassical handcrafted features which are neither general nor representative. Inthis paper, we introduce a new, yet conceptually simple, neural architecture,termed SpinNet, to extract local features which are rotationally invariantwhilst sufficiently informative to enable accurate registration. A SpatialPoint Transformer is first introduced to map the input local surface into acarefully designed cylindrical space, enabling end-to-end optimization withSO(2) equivariant representation. A Neural Feature Extractor which leveragesthe powerful point-based and 3D cylindrical convolutional neural layers is thenutilized to derive a compact and representative descriptor for matching.Extensive experiments on both indoor and outdoor datasets demonstrate thatSpinNet outperforms existing state-of-the-art techniques by a large margin.More critically, it has the best generalization ability across unseen scenarioswith different sensor modalities. The code is available athttps://github.com/QingyongHu/SpinNet.

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration