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 has drawn broader attentions due to its increasingdemands in various fields. Despite the impressive performance has been achievedon several databases, researchers neglect the fact that the orientation ofthose point cloud data is aligned. Varying the orientation of point cloud maylead to the degradation of performance, restricting the capacity ofgeneralizing to real applications where the prior of orientation is oftenunknown. In this paper, we propose the point projection feature, which isinvariant to the rotation of the input point cloud. A novel architecture isdesigned to mine features of different levels. We adopt a PointNet-basedbackbone to extract global feature for point cloud, and the graph aggregationoperation to perceive local shape structure. Besides, we introduce an efficientkey point descriptor to assign each point with different response and helprecognize the overall geometry. Mathematical analyses and experimental resultsdemonstrate that the proposed method can extract strictly rotation-invariantrepresentations for point cloud recognition and segmentation without dataaugmentation, and outperforms other state-of-the-art methods.

SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation