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

Downsampling and feature extraction are essential procedures for 3D pointcloud understanding. Existing methods are limited by the inconsistent pointdensities of different parts in the point cloud. In this work, we analyze thelimitation of the downsampling stage and propose the pre-abstraction group-wisewindow-normalization module. In particular, the window-normalization method isleveraged to unify the point densities in different parts. Furthermore, thegroup-wise strategy is proposed to obtain multi-type features, includingtexture and spatial information. We also propose the pre-abstraction module tobalance local and global features. Extensive experiments show that our moduleperforms better on several tasks. In segmentation tasks on S3DIS (Area 5), theproposed module performs better on small object recognition, and the resultshave more precise boundaries than others. The recognition of the sofa and thecolumn is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively.The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are77.6%/85.8%/91.7%. It outperforms the best model PointNeXt-XL(74.9%/83.0%/90.3%) by 2.7% on mIoU and achieves state-of-the-art performance.The code and models are available athttps://github.com/DBDXSS/Window-Normalization.git.

Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities