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

In recent years 3D object detection from LiDAR point clouds has made greatprogress thanks to the development of deep learning technologies. Althoughvoxel or point based methods are popular in 3D object detection, they usuallyinvolve time-consuming operations such as 3D convolutions on voxels or ballquery among points, making the resulting network inappropriate for timecritical applications. On the other hand, 2D view-based methods feature highcomputing efficiency while usually obtaining inferior performance than thevoxel or point based methods. In this work, we present a real-time view-basedsingle stage 3D object detector, namely CVFNet to fulfill this task. Tostrengthen the cross-view feature learning under the condition of demandingefficiency, our framework extracts the features of different views and fusesthem in an efficient progressive way. We first propose a novel Point-Rangefeature fusion module that deeply integrates point and range view features inmultiple stages. Then, a special Slice Pillar is designed to well maintain the3D geometry when transforming the obtained deep point-view features into bird'seye view. To better balance the ratio of samples, a sparse pillar detectionhead is presented to focus the detection on the nonempty grids. We conductexperiments on the popular KITTI and NuScenes benchmark, and state-of-the-artperformances are achieved in terms of both accuracy and speed.

CVFNet: Real-time 3D Object Detection by Learning Cross View Features