AI Paper Atlas

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

Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers

Robin Kim, Colin Samplawski, Benjamin Marlin

ECCV 2026 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 0 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
probe query embedding instead of 2D bounding box (linear) (ablation)DETR · Virtual KITTI 2 depthMAE (m): 4.27 -> 1.01Improved
probe query embedding instead of 2D bounding box (MLP) (ablation)DETR · Virtual KITTI 2 depthMAE (m): 1.02 -> 0.54Improved
probe query embedding instead of 2D bounding box (linear) (ablation)DETR · NYUv2 depthMAE (m): 0.87 -> 0.58Improved
probe query embedding instead of 2D bounding box (MLP) (ablation)DETR · NYUv2 depthMAE (m): 0.77 -> 0.51Improved
use MLP probe instead of linear probe (ablation)DETR · Virtual KITTI 2 depthMAE (m): 1.01 -> 0.54Improved
use MLP probe instead of linear probe (ablation)DETR · NYUv2 depthMAE (m): 0.58 -> 0.51Improved
use MLP probe instead of linear probe (ablation)RT-DETR v2 · Virtual KITTI 2 depthMAE (m): 1.56 -> 1.05Improved
learn an MLP output head on Depth Anything 2 instead of zero-shot (ablation)Depth Anything 2 · Virtual KITTI 2 depthMAE (m): 1.49 -> 0.50Improved
learn an MLP output head on Depth Anything 2 instead of zero-shot (ablation)Depth Anything 2 · NYUv2 depthMAE (m): 0.61 -> 0.36Improved
learn an MLP output head on MonoDETR instead of zero-shot (ablation)MonoDETR · NYUv2 depthMAE (m): 10.59 -> 0.75Improved
compare real-time detectors RT-DETR v2 against DETR with MLP probeRT-DETR v2 · Virtual KITTI 2 depthMAE (m): 0.54 -> 1.05Hurt
compare 3D-supervised MonoDETR against 2D DETR MLP probeDETR · KITTI 3D center predictionCenter MAE (m): 0.50 vs 0.30Hurt

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