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

We present a Non-parametric Network for 3D point cloud analysis, Point-NN,which consists of purely non-learnable components: farthest point sampling(FPS), k-nearest neighbors (k-NN), and pooling operations, with trigonometricfunctions. Surprisingly, it performs well on various 3D tasks, requiring noparameters or training, and even surpasses existing fully trained models.Starting from this basic non-parametric model, we propose two extensions.First, Point-NN can serve as a base architectural framework to constructParametric Networks by simply inserting linear layers on top. Given thesuperior non-parametric foundation, the derived Point-PN exhibits a highperformance-efficiency trade-off with only a few learnable parameters. Second,Point-NN can be regarded as a plug-and-play module for the already trained 3Dmodels during inference. Point-NN captures the complementary geometricknowledge and enhances existing methods for different 3D benchmarks withoutre-training. We hope our work may cast a light on the community forunderstanding 3D point clouds with non-parametric methods. Code is available athttps://github.com/ZrrSkywalker/Point-NN.

Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis