Research map / Detection and segmentation / 3D detection and driving
Exploring Geometric Consistency for Monocular 3D Object Detection
Qing Lian, Botao Ye, Ruijia Xu, Weilong Yao, Tong Zhang
Check 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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add all four geometry-aware augmentations | M3D-RPN · KITTI test, Car 3D | AP|40: 16.45 -> 20.34; 11.24 -> 14.27; 10.02 -> 12.02 | Improved |
| Add all four geometry-aware augmentations | CenterNet · KITTI test, Car 3D | AP|40: 19.41 -> 23.41; 13.21 -> 15.26; 11.04 -> 12.80 | Improved |
| Use geometry-aware augmentation instead of vanilla augmentation | CenterNet · nuScenes validation | mAP: 33.2 -> 34.5 | Improved |
| Use geometry-aware augmentation instead of vanilla augmentation | CenterNet · nuScenes validation | mATE: 0.69 -> 0.68 | Improved |
| Use geometry-aware augmentation instead of vanilla augmentation | CenterNet · nuScenes validation | NDS: 38.4 -> 39.4 | Improved |
| Add geometry-aware random scale (ablation) | M3D-RPN · KITTI validation, Car Easy | AP|40: 18.21 -> 22.06 | Improved |
| Add geometry-aware random crop (ablation) | M3D-RPN · KITTI validation, Car Easy | AP|40: 18.21 -> 20.91 | Improved |
| Add camera movement augmentation (ablation) | M3D-RPN · KITTI validation, Car Easy | AP|40: 18.21 -> 21.73 | Improved |
| Add geometry-aware copy-paste (ablation) | M3D-RPN · KITTI validation, Car Easy | AP|40: 18.21 -> 22.63 | Improved |
| Add geometry-aware random scale (ablation) | CenterNet · KITTI validation, Car Easy | AP|40: 20.16 -> 22.46 | Improved |
| Add geometry-aware random crop (ablation) | CenterNet · KITTI validation, Car Easy | AP|40: 20.16 -> 22.63 | Improved |
| Add camera movement augmentation (ablation) | CenterNet · KITTI validation, Car Easy | AP|40: 20.16 -> 21.34 | Improved |
Closest papers by meaning
- Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation (NeurIPS 2026 · similarity 0.91)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.89)
- Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency (ECCV 2022 · similarity 0.89)
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection (NeurIPS 2026 · similarity 0.89)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.89)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.88)
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.
