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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

3D object detection algorithms for autonomous driving reason about 3Dobstacles either from 3D birds-eye view or perspective view or both. Recentworks attempt to improve the detection performance via mining and fusing frommultiple egocentric views. Although the egocentric perspective view alleviatessome weaknesses of the birds-eye view, the sectored grid partition becomes socoarse in the distance that the targets and surrounding context mix together,which makes the features less discriminative. In this paper, we generalize theresearch on 3D multi-view learning and propose a novel multi-view-based 3Ddetection method, named X-view, to overcome the drawbacks of the multi-viewmethods. Specifically, X-view breaks through the traditional limitation aboutthe perspective view whose original point must be consistent with the 3DCartesian coordinate. X-view is designed as a general paradigm that can beapplied on almost any 3D detectors based on LiDAR with only little increment ofrunning time, no matter it is voxel/grid-based or raw-point-based. We conductexperiments on KITTI and NuScenes datasets to demonstrate the robustness andeffectiveness of our proposed X-view. The results show that X-view obtainsconsistent improvements when combined with four mainstream state-of-the-art 3Dmethods: SECOND, PointRCNN, Part-A^2, and PV-RCNN.

X-view: Non-egocentric Multi-View 3D Object Detector