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

Vision-based Bird's Eye View (BEV) representation is an emerging perceptionformulation for autonomous driving. The core challenge is to construct BEVspace with multi-camera features, which is a one-to-many ill-posed problem.Diving into all previous BEV representation generation methods, we found thatmost of them fall into two types: modeling depths in image views or modelingheights in the BEV space, mostly in an implicit way. In this work, we proposeto explicitly model heights in the BEV space, which needs no extra data likeLiDAR and can fit arbitrary camera rigs and types compared to modeling depths.Theoretically, we give proof of the equivalence between height-based methodsand depth-based methods. Considering the equivalence and some advantages ofmodeling heights, we propose HeightFormer, which models heights anduncertainties in a self-recursive way. Without any extra data, the proposedHeightFormer could estimate heights in BEV accurately. Benchmark results showthat the performance of HeightFormer achieves SOTA compared with thosecamera-only methods.

HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View