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

Raw point clouds data inevitably contains outliers or noise throughacquisition from 3D sensors or reconstruction algorithms. In this paper, wepresent a novel end-to-end network for robust point clouds processing, namedPointASNL, which can deal with point clouds with noise effectively. The keycomponent in our approach is the adaptive sampling (AS) module. It firstre-weights the neighbors around the initial sampled points from farthest pointsampling (FPS), and then adaptively adjusts the sampled points beyond theentire point cloud. Our AS module can not only benefit the feature learning ofpoint clouds, but also ease the biased effect of outliers. To further capturethe neighbor and long-range dependencies of the sampled point, we proposed alocal-nonlocal (L-NL) module inspired by the nonlocal operation. Such L-NLmodule enables the learning process insensitive to noise. Extensive experimentsverify the robustness and superiority of our approach in point cloudsprocessing tasks regardless of synthesis data, indoor data, and outdoor datawith or without noise. Specifically, PointASNL achieves state-of-the-art robustperformance for classification and segmentation tasks on all datasets, andsignificantly outperforms previous methods on real-world outdoor SemanticKITTIdataset with considerate noise. Our code is released throughhttps://github.com/yanx27/PointASNL.

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling