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

Accurately describing and detecting 2D and 3D keypoints is crucial toestablishing correspondences across images and point clouds. Despite a plethoraof learning-based 2D or 3D local feature descriptors and detectors having beenproposed, the derivation of a shared descriptor and joint keypoint detectorthat directly matches pixels and points remains under-explored by thecommunity. This work takes the initiative to establish fine-grainedcorrespondences between 2D images and 3D point clouds. In order to directlymatch pixels and points, a dual fully convolutional framework is presented thatmaps 2D and 3D inputs into a shared latent representation space tosimultaneously describe and detect keypoints. Furthermore, an ultra-widereception mechanism in combination with a novel loss function are designed tomitigate the intrinsic information variations between pixel and point localregions. Extensive experimental results demonstrate that our framework showscompetitive performance in fine-grained matching between images and pointclouds and achieves state-of-the-art results for the task of indoor visuallocalization. Our source code will be available at [no-name-for-blind-review].

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching