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/

Zendy Plus

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

Zendy Tools

Zendy Open

Real-time 3D object detection is crucial for autonomous cars. Achievingpromising performance with high efficiency, voxel-based approaches havereceived considerable attention. However, previous methods model the inputspace with features extracted from equally divided sub-regions withoutconsidering that point cloud is generally non-uniformly distributed over thespace. To address this issue, we propose a novel 3D object detection frameworkwith dynamic information modeling. The proposed framework is designed in acoarse-to-fine manner. Coarse predictions are generated in the first stage viaa voxel-based region proposal network. We introduce InfoFocus, which improvesthe coarse detections by adaptively refining features guided by the informationof point cloud density. Experiments are conducted on the large-scale nuScenes3D detection benchmark. Results show that our framework achieves thestate-of-the-art performance with 31 FPS and improves our baselinesignificantly by 9.0% mAP on the nuScenes test set.

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling