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

Semantic segmentation in bird's eye view (BEV) is an important task forautonomous driving. Though this task has attracted a large amount of researchefforts, it is still challenging to flexibly cope with arbitrary (single ormultiple) camera sensors equipped on the autonomous vehicle. In this paper, wepresent BEVSegFormer, an effective transformer-based method for BEV semanticsegmentation from arbitrary camera rigs. Specifically, our method first encodesimage features from arbitrary cameras with a shared backbone. These imagefeatures are then enhanced by a deformable transformer-based encoder. Moreover,we introduce a BEV transformer decoder module to parse BEV semanticsegmentation results. An efficient multi-camera deformable attention unit isdesigned to carry out the BEV-to-image view transformation. Finally, thequeries are reshaped according the layout of grids in the BEV, and upsampled toproduce the semantic segmentation result in a supervised manner. We evaluatethe proposed algorithm on the public nuScenes dataset and a self-collecteddataset. Experimental results show that our method achieves promisingperformance on BEV semantic segmentation from arbitrary camera rigs. We alsodemonstrate the effectiveness of each component via ablation study.

BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs