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

Currently, there have been many kinds of voxel-based 3D single stagedetectors, while point-based single stage methods are still underexplored. Inthis paper, we first present a lightweight and effective point-based 3D singlestage object detector, named 3DSSD, achieving a good balance between accuracyand efficiency. In this paradigm, all upsampling layers and refinement stage,which are indispensable in all existing point-based methods, are abandoned toreduce the large computation cost. We novelly propose a fusion samplingstrategy in downsampling process to make detection on less representativepoints feasible. A delicate box prediction network including a candidategeneration layer, an anchor-free regression head with a 3D center-nessassignment strategy is designed to meet with our demand of accuracy and speed.Our paradigm is an elegant single stage anchor-free framework, showing greatsuperiority to other existing methods. We evaluate 3DSSD on widely used KITTIdataset and more challenging nuScenes dataset. Our method outperforms allstate-of-the-art voxel-based single stage methods by a large margin, and hascomparable performance to two stage point-based methods as well, with inferencespeed more than 25 FPS, 2x faster than former state-of-the-art point-basedmethods.

3DSSD: Point-based 3D Single Stage Object Detector