AI Paper Atlas

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

Object as Query: Lifting Any 2D Object Detector to 3D Detection

Zitian Wang, Zehao Huang, Jiahui Fu, Naiyan Wang, Si Liu

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 63 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
replace fixed queries with dynamically generated queries from a 2D detector (ablation)MV2D (ResNet-50) · nuScenes valmAP: 36.2 -> 38.0Improved
increase number of fixed queries from 300 to 1500 (ablation)fixed-query baseline · nuScenes valNDS: 39.4 -> 40.6Improved
restrict cross attention to relevant features by top1 IoU rule (ablation)MV2D · nuScenes valNDS: 41.2 -> 42.4Improved
use all overlapped rule instead of top1 IoU (ablation)MV2D · nuScenes valNDS: 42.4 -> 42.6Improved
add history frame input (ablation)MV2D · nuScenes valNDS: 42.6 -> 51.1Improved
use MV2D instead of fixed-query baseline with history (ablation)MV2D · nuScenes valNDS: 47.4 -> 51.1Improved
use query generator with equivalent intrinsics instead of uniform depth sampling or scale-based depth (ablation)MV2D · nuScenes valNDS: 40.1 / 40.8 -> 42.6Improved
use relevant-object-region cross attention instead of deformable attention (ablation)MV2D · nuScenes valNDS: 48.4 -> 51.1Improved
use lighter 2D detector (YOLOX) instead of Faster R-CNN (ablation)MV2D · nuScenes valmAP: 41.4 -> 41.3No clear effect
use nuImages pre-training instead of COCO (ablation)MV2D · nuScenes valNDS: 49.8 -> 51.1Improved
increase decoder layers from 1 to 2 (ablation)MV2D · nuScenes valmAP: 36.4 -> 39.1 (+2.7)Improved
use MV2D-T instead of PETRv2 on val setResNet-101 · nuScenes valmAP: 0.421 -> 0.471Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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