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

As a primitive 3D data representation, point clouds are prevailing in 3Dsensing, yet short of intrinsic structural information of the underlyingobjects. Such discrepancy poses great challenges on directly establishingcorrespondences between point clouds sampled from deformable shapes. In lightof this, we propose Neural Intrinsic Embedding (NIE) to embed each vertex intoa high-dimensional space in a way that respects the intrinsic structure. Basedupon NIE, we further present a weakly-supervised learning framework fornon-rigid point cloud registration. Unlike the prior works, we do not requireexpansive and sensitive off-line basis construction (e.g., eigen-decompositionof Laplacians), nor do we require ground-truth correspondence labels forsupervision. We empirically show that our framework performs on par with oreven better than the state-of-the-art baselines, which generally require moresupervision and/or more structural geometric input.

Neural Intrinsic Embedding for Non-rigid Point Cloud Matching