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

3D object detection with surround-view images is an essential task forautonomous driving. In this work, we propose DETR4D, a Transformer-basedframework that explores sparse attention and direct feature query for 3D objectdetection in multi-view images. We design a novel projective cross-attentionmechanism for query-image interaction to address the limitations of existingmethods in terms of geometric cue exploitation and information loss forcross-view objects. In addition, we introduce a heatmap generation techniquethat bridges 3D and 2D spaces efficiently via query initialization.Furthermore, unlike the common practice of fusing intermediate spatial featuresfor temporal aggregation, we provide a new perspective by introducing a novelhybrid approach that performs cross-frame fusion over past object queries andimage features, enabling efficient and robust modeling of temporal information.Extensive experiments on the nuScenes dataset demonstrate the effectiveness andefficiency of the proposed DETR4D.

DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention