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

We present PPF-FoldNet for unsupervised learning of 3D local descriptors onpure point cloud geometry. Based on the folding-based auto-encoding of wellknown point pair features, PPF-FoldNet offers many desirable properties: itnecessitates neither supervision, nor a sensitive local reference frame,benefits from point-set sparsity, is end-to-end, fast, and can extract powerfulrotation invariant descriptors. Thanks to a novel feature visualization, itsevolution can be monitored to provide interpretable insights. Our extensiveexperiments demonstrate that despite having six degree-of-freedom invarianceand lack of training labels, our network achieves state of the art results instandard benchmark datasets and outperforms its competitors when rotations andvarying point densities are present. PPF-FoldNet achieves $9\%$ higher recallon standard benchmarks, $23\%$ higher recall when rotations are introduced intothe same datasets and finally, a margin of $>35\%$ is attained when pointdensity is significantly decreased.

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors