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/

Zendy Plus

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

Zendy Tools

Zendy Open

Point cloud analysis without pose priors is very challenging in realapplications, as the orientations of point clouds are often unknown. In thispaper, we propose a brand new point-set learning framework PRIN, namely,Pointwise Rotation-Invariant Network, focusing on rotation-invariant featureextraction in point clouds analysis. We construct spherical signals by DensityAware Adaptive Sampling to deal with distorted point distributions in sphericalspace. In addition, we propose Spherical Voxel Convolution and PointRe-sampling to extract rotation-invariant features for each point. Our networkcan be applied to tasks ranging from object classification, part segmentation,to 3D feature matching and label alignment. We show that, on the dataset withrandomly rotated point clouds, PRIN demonstrates better performance thanstate-of-the-art methods without any data augmentation. We also providetheoretical analysis for the rotation-invariance achieved by our methods.

Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution