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 structures of 3D shapes is a fundamental problem in the field ofcomputer graphics and geometry processing. We present a simple yetinterpretable unsupervised method for learning a new structural representationin the form of 3D structure points. The 3D structure points produced by ourmethod encode the shape structure intrinsically and exhibit semanticconsistency across all the shape instances with similar structures. This is achallenging goal that has not fully been achieved by other methods.Specifically, our method takes a 3D point cloud as input and encodes it as aset of local features. The local features are then passed through a novel pointintegration module to produce a set of 3D structure points. The chamferdistance is used as reconstruction loss to ensure the structure points lieclose to the input point cloud. Extensive experiments have shown that ourmethod outperforms the state-of-the-art on the semantic shape correspondencetask and achieves comparable performance with the state-of-the-art on thesegmentation label transfer task. Moreover, the PCA based shape embedding builtupon consistent structure points demonstrates good performance in preservingthe shape structures. Code is available athttps://github.com/NolenChen/3DStructurePoints

Unsupervised Learning of Intrinsic Structural Representation Points