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

Transformer has demonstrated promising performance in many 2D vision tasks.However, it is cumbersome to compute the self-attention on large-scale pointcloud data because point cloud is a long sequence and unevenly distributed in3D space. To solve this issue, existing methods usually compute self-attentionlocally by grouping the points into clusters of the same size, or performconvolutional self-attention on a discretized representation. However, theformer results in stochastic point dropout, while the latter typically hasnarrow attention fields. In this paper, we propose a novel voxel-basedarchitecture, namely Voxel Set Transformer (VoxSeT), to detect 3D objects frompoint clouds by means of set-to-set translation. VoxSeT is built upon avoxel-based set attention (VSA) module, which reduces the self-attention ineach voxel by two cross-attentions and models features in a hidden spaceinduced by a group of latent codes. With the VSA module, VoxSeT can managevoxelized point clusters with arbitrary size in a wide range, and process themin parallel with linear complexity. The proposed VoxSeT integrates the highperformance of transformer with the efficiency of voxel-based model, which canbe used as a good alternative to the convolutional and point-based backbones.VoxSeT reports competitive results on the KITTI and Waymo detection benchmarks.The source codes can be found at \url{https://github.com/skyhehe123/VoxSeT}.

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds