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

LiDAR and camera are two essential sensors for 3D object detection inautonomous driving. LiDAR provides accurate and reliable 3D geometryinformation while the camera provides rich texture with color. Despite theincreasing popularity of fusing these two complementary sensors, the challengeremains in how to effectively fuse 3D LiDAR point cloud with 2D camera images.Recent methods focus on point-level fusion which paints the LiDAR point cloudwith camera features in the perspective view or bird's-eye view (BEV)-levelfusion which unifies multi-modality features in the BEV representation. In thispaper, we rethink these previous fusion strategies and analyze theirinformation loss and influences on geometric and semantic features. We presentSemanticBEVFusion to deeply fuse camera features with LiDAR features in aunified BEV representation while maintaining per-modality strengths for 3Dobject detection. Our method achieves state-of-the-art performance on thelarge-scale nuScenes dataset, especially for challenging distant objects. Thecode will be made publicly available.

SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection