Research map / Detection and segmentation / 3D detection and driving
Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
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 extrinsic regression and feature transfer to SMOKE (ablation) | SMOKE · KITTI Odometry sequence 00 | AP3D: 34.98 -> 41.78 | Helped |
| add extrinsic regression and feature transfer to M3D-RPN (ablation) | M3D-RPN · KITTI Odometry sequence 00 | AP3D: 36.13 -> 41.36 | Helped |
| add extrinsic regression and feature transfer to Kinematic3D (ablation) | Kinematic3D · KITTI Odometry sequence 00 | AP3D: 41.44 -> 48.92 | Helped |
| use MonoEF instead of SMOKE baseline | SMOKE · KITTI3D validation, car Moderate, disturbed | AP3D: 35.09 -> 70.86 | Helped |
| apply artificial camera extrinsic perturbation | SMOKE · KITTI3D validation, car Moderate | AP3D: 72.80 -> 35.09 | Hurt |
| apply artificial camera extrinsic perturbation | MonoEF · KITTI3D validation, car Moderate | AP3D: 72.83 -> 70.86 | Hurt |
| add camera-extrinsic-aware amendment | SMOKE baseline · nuScenes test, overall | ATE: 0.87 -> 0.77 | Helped |
| add camera-extrinsic-aware amendment | SMOKE baseline · nuScenes test, overall | ASE: 0.57 -> 0.37 | Helped |
| add camera-extrinsic-aware amendment | SMOKE baseline · nuScenes test, overall | AOE: 0.75 -> 0.65 | Helped |
| add extrinsic amendment (ablation) | SMOKE · KITTI Odometry sequence 00 | AP2D: 80.51 -> 79.33 | Hurt |
Closest papers by meaning
- MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues (NeurIPS 2023 · similarity 0.90)
- Monocular 3D Object Detection for Autonomous Driving (CVPR 2016 · similarity 0.89)
- Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · similarity 0.88)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.87)
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.87)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · 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.