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

3D point cloud interpretation is a challenging task due to the randomness andsparsity of the component points. Many of the recently proposed methods likePointNet and PointCNN have been focusing on learning shape descriptions frompoint coordinates as point-wise input features, which usually involvescomplicated network architectures. In this work, we draw attention back to thestandard 3D convolutions towards an efficient 3D point cloud interpretation.Instead of converting the entire point cloud into voxel representations likethe other volumetric methods, we voxelize the sub-portions of the point cloudonly at necessary locations within each convolution layer on-the-fly, using ourdynamic voxelization operation with self-adaptive voxelization resolution. Inaddition, we incorporate 3D group convolution into our dense convolution kernelimplementation to further exploit the rotation invariant features of pointcloud. Benefiting from its simple fully-convolutional architecture, our networkis able to run and converge at a considerably fast speed, while yields on-paror even better performance compared with the state-of-the-art methods onseveral benchmark datasets.

DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution