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

Recently, perception task based on Bird's-Eye View (BEV) representation hasdrawn more and more attention, and BEV representation is promising as thefoundation for next-generation Autonomous Vehicle (AV) perception. However,most existing BEV solutions either require considerable resources to executeon-vehicle inference or suffer from modest performance. This paper proposes asimple yet effective framework, termed Fast-BEV , which is capable ofperforming faster BEV perception on the on-vehicle chips. Towards this goal, wefirst empirically find that the BEV representation can be sufficiently powerfulwithout expensive transformer based transformation nor depth representation.Our Fast-BEV consists of five parts, We novelly propose (1) a lightweightdeployment-friendly view transformation which fast transfers 2D image featureto 3D voxel space, (2) an multi-scale image encoder which leverages multi-scaleinformation for better performance, (3) an efficient BEV encoder which isparticularly designed to speed up on-vehicle inference. We further introduce(4) a strong data augmentation strategy for both image and BEV space to avoidover-fitting, (5) a multi-frame feature fusion mechanism to leverage thetemporal information. Through experiments, on 2080Ti platform, our R50 modelcan run 52.6 FPS with 47.3% NDS on the nuScenes validation set, exceeding the41.3 FPS and 47.5% NDS of the BEVDepth-R50 model and 30.2 FPS and 45.7% NDS ofthe BEVDet4D-R50 model. Our largest model (R101@900x1600) establishes acompetitive 53.5% NDS on the nuScenes validation set. We further develop abenchmark with considerable accuracy and efficiency on current popularon-vehicle chips. The code is released at:https://github.com/Sense-GVT/Fast-BEV.

Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline