Research map / Detection and segmentation / 3D detection and driving
MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
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 |
|---|---|---|---|
| Add depth and projected-offset uncertainty prediction to the detector (ablation) | Baseline · KITTI3D validation car Moderate | AP3D, IoU 0.5: 33.19 -> 41.46 | Helped |
| Add depth uncertainty prediction (ablation) | Baseline · KITTI3D validation car Moderate | AP3D, IoU 0.5: 33.19 -> 40.46 | Helped |
| Add projected-offset uncertainty prediction (ablation) | Baseline · KITTI3D validation car Moderate | AP3D, IoU 0.5: 33.19 -> 38.75 | Helped |
| Add depth uncertainty rather than projected-offset uncertainty (ablation) | Baseline · KITTI3D validation car Moderate | AP3D, IoU 0.5: 38.75 -> 40.46 | Helped |
| Add pairwise spatial constraint prediction and optimization (ablation) | +σᶻ+σᵘᵛ · KITTI3D validation car Moderate | AP3D, IoU 0.5: 41.46 -> 42.39 | Helped |
| Add pairwise optimization (ablation) | +σᶻ+σᵘᵛ · KITTI3D validation car Moderate, IoU 0.7, 0–1 pairs | AP3D: 5.41 -> 6.02 | Helped |
| Add pairwise optimization (ablation) | +σᶻ+σᵘᵛ · KITTI3D validation car Moderate, IoU 0.7, 2–4 pairs | AP3D: 8.46 -> 8.97 | Helped |
| Add pairwise optimization (ablation) | +σᶻ+σᵘᵛ · KITTI3D validation car Moderate, IoU 0.7, 5–8 pairs | AP3D: 14.63 -> 15.54 | Helped |
| Use uncertainty estimates to weight optimization errors (ablation) | MonoPair spatial constraint optimization · KITTI3D validation | detection performance | Helped |
| Replace uncertainty-based weights with identity or hand-designed weights (ablation) | MonoPair spatial constraint optimization · KITTI3D validation | detection performance | Hurt |
| Increase pair count from 0–1 to 5–8 constraints (ablation) | MonoPair · KITTI3D validation car Moderate, IoU 0.7 | AP3D: 6.02 -> 15.54 | Helped |
| Use pairwise constraints across varying pair counts (ablation) | MonoPair · KITTI3D validation car Moderate, IoU 0.7, 9 or more pairs | AP3D | No clear effect |
Closest papers by meaning
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.89)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.89)
- UniMODE: Unified Monocular 3D Object Detection (CVPR 2024 · similarity 0.88)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.88)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.87)
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.