AI Paper Atlas

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

MAESTRO: Task-Relevant Optimization via Adaptive Feature Enhancement and Suppression for Multi-task 3D Perception

Changwon Kang, Jisong Kim, Hongjae Shin, Junseo Park, Jun Won Choi

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 1 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 CPG (ablation)Baseline-MTL · nuScenes val (1/4 train subset, ablation)mIoU (Occ3D occupancy): 33.6 -> 34.6Improved
add TSFG to detection only (ablation)Baseline-MTL with CPG · nuScenes val (1/4 train subset, ablation)mAP (3D detection): 31.3 -> 32.6Mixed
add TSFG to map only (ablation)Baseline-MTL with CPG · nuScenes val (1/4 train subset, ablation)mIoU (BEV map): 40.3 -> 44.0Mixed
add TSFG to all three tasks (ablation)Baseline-MTL with CPG · nuScenes val (1/4 train subset, ablation)mIoU (BEV map): 40.3 -> 44.1Improved
add TSFG to all three tasks (ablation)Baseline-MTL with CPG · nuScenes val (1/4 train subset, ablation)mIoU (Occ3D occupancy): 34.6 -> 35.9Improved
add SPA (ablation)MAESTRO without SPA · nuScenes val (1/4 train subset, ablation)mIoU (Occ3D occupancy): 35.9 -> 36.9Improved
add prototype-wise features (ablation)CPG baseline · nuScenes val (1/4 train subset, ablation)mIoU (BEV map): 40.3 -> 42.1Improved
add prototype-aware features (ablation)TSFG · nuScenes val (1/4 train subset, ablation)mIoU (BEV map): 42.1 -> 43.4Improved
add feature suppression (ablation)TSFG · nuScenes val (1/4 train subset, ablation)mIoU (BEV map): 43.4 -> 44.1Improved
add map prototypes to occupancy prototypes (ablation)SPA · nuScenes val (1/4 train subset, ablation)mIoU (Occ3D occupancy): 36.3 -> 36.9Improved
add detection prototypes to occupancy prototypes (ablation)SPA · nuScenes val (1/4 train subset, ablation)mIoU (Occ3D occupancy): 35.9 -> 36.3Improved
use MAESTRO instead of naive shared-backbone MTLBaseline-MTL · nuScenes valmAP (3D detection): 32.7 -> 36.4Improved

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