AI Paper Atlas

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

Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection

Soyul Lee, Seungmin Baek, Dongbo Min

AAAI 2026 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object 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
add difficulty-aware label-guided denoising (MonoDLGD)MonoDGP · KITTI val Car AP3D ModerateAP3D R40: 22.34 -> 25.19Improved
add the method on top of MonoDETRMonoDETR · KITTI val Car AP3D EasyAP3D R40: 27.34 -> 29.79Improved
swap anchor queries for 3D-DAB without denoising supervision (ablation)MonoDGP · KITTI val Car AP3D ModerateAP3D R40: 22.34 -> 20.64Hurt
add uniform label perturbation to 3D-DAB (ablation)3D-DAB · KITTI val Car AP3D ModerateAP3D R40: 20.64 -> 23.82Improved
add Laplacian uncertainty loss to uniform noise denoising (ablation)uniform noise denoising · KITTI val Car AP3D ModerateAP3D R40: 23.82 -> 24.7Improved
replace uniform noise with difficulty-aware perturbation (ablation)3D-DAB + LU · KITTI val Car AP3D ModerateAP3D R40: 24.7 -> 25.19Improved
add depth to denoising targets (ablation)Bbox + Class denoising · KITTI val Car AP3D ModerateAP3D R40: 23.36 -> 25.19Improved
use ground-truth labels instead of uniform-noised labels in stage 1 (ablation)DAP stage 1 · KITTI val Car AP3D ModerateAP3D R40: 23.85 -> 25.19Improved
add EMA to difficulty min/max normalization (beta 0.8) (ablation)DAP · KITTI val Car AP3D ModerateAP3D R40: 24.32 -> 25.19Improved
vary EMA momentum to 0.9 (ablation)DAP · KITTI val Car AP3D ModerateAP3D R40: 25.19 -> 24.29Hurt
increase perturbation groups from 7 to 8 (ablation)MonoDLGD · KITTI val Car AP3D ModerateAP3D R40: 25.19 -> 23.93Hurt
vary bbox scale factor gamma^b from 0.4 to 0.2 (ablation)DAP · KITTI val Car AP3D EasyAP3D R40: 34.89 -> 32.02Hurt

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