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

This paper presents an effective normal estimation method adoptingmulti-patch stitching for an unstructured point cloud. The majority oflearning-based approaches encode a local patch around each point of a wholemodel and estimate the normals in a point-by-point manner. In contrast, wesuggest a more efficient pipeline, in which we introduce a patch-level normalestimation architecture to process a series of overlapping patches.Additionally, a multi-normal selection method based on weights, dubbed asmulti-patch stitching, integrates the normals from the overlapping patches. Toreduce the adverse effects of sharp corners or noise in a patch, we introducean adaptive local feature aggregation layer to focus on an anisotropicneighborhood. We then utilize a multi-branch planar experts module to break themutual influence between underlying piecewise surfaces in a patch. At thestitching stage, we use the learned weights of multi-branch planar experts anddistance weights between points to select the best normal from the overlappingparts. Furthermore, we put forward constructing a sparse matrix representationto reduce large-scale retrieval overheads for the loop iterations dramatically.Extensive experiments demonstrate that our method achieves SOTA results withthe advantage of lower computational costs and higher robustness to noise overmost of the existing approaches.

Fast and Accurate Normal Estimation for Point Cloud via Patch Stitching