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

Point cloud registration is the process of aligning a pair of point sets viasearching for a geometric transformation. Unlike classical optimization-basedmethods, recent learning-based methods leverage the power of deep learning forregistering a pair of point sets. In this paper, we propose to develop a novelmodel that organically integrates the optimization to learning, aiming toaddress the technical challenges in 3D registration. More specifically, inaddition to the deep transformation decoding network, our framework introducean optimizable deep \underline{S}patial \underline{C}orrelation\underline{R}epresentation (SCR) feature. The SCR feature and weights of thetransformation decoder network are jointly updated towards the minimization ofan unsupervised alignment loss. We further propose an adaptive Chamfer loss foraligning partial shapes. To verify the performance of our proposed method, weconducted extensive experiments on the ModelNet40 dataset. The resultsdemonstrate that our method achieves significantly better performance than theprevious state-of-the-art approaches in the full/partial point set registrationtask.

Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector