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

Most existing point cloud completion methods are only applicable to partialpoint clouds without any noises and outliers, which does not always hold inpractice. We propose in this paper an end-to-end network, named CS-Net, tocomplete the point clouds contaminated by noises or containing outliers. In ourCS-Net, the completion and segmentation modules work collaboratively to promoteeach other, benefited from our specifically designed cascaded structure. Withthe help of segmentation, more clean point cloud is fed into the completionmodule. We design a novel completion decoder which harnesses the labelsobtained by segmentation together with FPS to purify the point cloud andleverages KNN-grouping for better generation. The completion and segmentationmodules work alternately share the useful information from each other togradually improve the quality of prediction. To train our network, we build adataset to simulate the real case where incomplete point clouds containoutliers. Our comprehensive experiments and comparisons againststate-of-the-art completion methods demonstrate our superiority. We alsocompare with the scheme of segmentation followed by completion and theirend-to-end fusion, which also proves our efficacy.

Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation