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

Learning and selecting important points on a point cloud is crucial for pointcloud understanding in various applications. Most of early methods selected theimportant points on 3D shapes by analyzing the intrinsic geometric propertiesof every single shape, which fails to capture the importance of points thatdistinguishes a shape from objects of other classes, i.e., the distinction ofpoints. To address this problem, we propose D-Net (Distinctive Network) tolearn for distinctive point clouds based on a self-attentive point searchingand a learnable feature fusion. Specifically, in the self-attentive pointsearching, we first learn the distinction score for each point to reveal thedistinction distribution of the point cloud. After ranking the learneddistinction scores, we group a point cloud into a high distinctive point setand a low distinctive one to enrich the fine-grained point cloud structure. Togenerate a compact feature representation for each distinctive point set, astacked self-gated convolution is proposed to extract the distinctive features.Finally, we further introduce a learnable feature fusion mechanism to aggregatemultiple distinctive features into a global point cloud representation in achannel-wise aggregation manner. The results also show that the learneddistinction distribution of a point cloud is highly consistent with objects ofthe same class and different from objects of other classes. Extensiveexperiments on public datasets, including ModelNet and ShapeNet part dataset,demonstrate the ability to learn for distinctive point clouds, which helps toachieve the state-of-the-art performance in some shape understandingapplications.

D-Net: Learning for Distinctive Point Clouds by Self-Attentive Point Searching and Learnable Feature Fusion