Research map / Detection and segmentation / 3D detection and driving
GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Train with GrooMeD-NMS rather than applying NMS only at inference | M3D-RPN-based monocular 3D detector · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.55 -> 14.32 | Helped |
| Add a confidence head (ablation) | GrooMeD-NMS detector · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 12.10 -> 13.89 | Helped |
| Add NMS training (ablation) | Confidence-head detector · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.89 -> 14.32 | Helped |
| Use confidence scores rather than classification scores for NMS (ablation) | GrooMeD-NMS detector · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 11.21 -> 14.32 | Helped |
| Add warmup initialization (ablation) | GrooMeD-NMS detector · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 11.68 -> 14.32 | Helped |
| Use linear rather than exponential pruning (τ=1) (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 9.26 -> 14.32 | Helped |
| Use linear rather than exponential pruning (τ=0.5) (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.85 -> 14.32 | Helped |
| Use linear rather than exponential pruning (τ=0.1) (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.79 -> 14.32 | Helped |
| Use linear rather than sigmoidal pruning (τ=0.1) (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.21 -> 14.32 | Helped |
| Add grouping (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.91 -> 14.32 | Helped |
| Add masking to grouped NMS (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.74 -> 14.32 | Helped |
| Use Imagewise AP rather than Vanilla AP loss (ablation) | GrooMeD-NMS · KITTI Val 1 Cars, 3D AP40 IoU≥0.7 Moderate | AP3D40: 13.73 -> 14.32 | Helped |
Closest papers by meaning
- Learning Non-Maximum Suppression (CVPR 2017 · similarity 0.89)
- Accelerating Non-Maximum Suppression: A Graph Theory Perspective (NeurIPS 2024 · similarity 0.89)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.86)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.86)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.86)
- UniMODE: Unified Monocular 3D Object Detection (CVPR 2024 · similarity 0.86)
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.