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

Accurate 3D object detection from point clouds has become a crucial componentin autonomous driving. However, the volumetric representations and theprojection methods in previous works fail to establish the relationshipsbetween the local point sets. In this paper, we propose Sparse Voxel-GraphAttention Network (SVGA-Net), a novel end-to-end trainable network which mainlycontains voxel-graph module and sparse-to-dense regression module to achievecomparable 3D detection tasks from raw LIDAR data. Specifically, SVGA-Netconstructs the local complete graph within each divided 3D spherical voxel andglobal KNN graph through all voxels. The local and global graphs serve as theattention mechanism to enhance the extracted features. In addition, the novelsparse-to-dense regression module enhances the 3D box estimation accuracythrough feature maps aggregation at different levels. Experiments on KITTIdetection benchmark demonstrate the efficiency of extending the graphrepresentation to 3D object detection and the proposed SVGA-Net can achievedecent detection accuracy.

SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds