AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention

Simon Doll, Richard Schulz, Lukas Schneider, Viviane Benzin, Markus Enzweiler, Hendrik P.A. Lensch

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add sensor-relative query projection P(Q) (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.248 -> 0.317Improved
add value projection P(V) to P(Q) (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.317 -> 0.313Hurt
add query-center visibility constraint C(Q) to P(Q) (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.317 -> 0.318Mixed
add C(Q) to P(Q)+P(V) (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.313 -> 0.319Improved
increase object queries from 600 to 900 (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.308 -> 0.313Improved
increase object queries from 900 to 1200 (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.313 -> 0.313No clear effect
increase decoder layers from 2 to 6 (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.308 -> 0.313Improved
increase decoder layers from 6 to 10 (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.313 -> 0.311No clear effect
share weights across decoder layers 2-6 (ablation)SpatialDETR · nuScenes val (ablation setup)mAP: 0.313 -> 0.314Improved
initialize backbone from FCOS3D checkpoint (PT)SpatialDETR · nuScenes valmAP: 0.303 -> 0.351Improved
use spatially-aware global attention instead of DETR3D center lookuptruck/bus AP · nuScenes valAP truck: 0.286 -> 0.302Improved
use spatially-aware global attention instead of DETR3Dbus AP · nuScenes valAP bus: 0.347 -> 0.378Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy