Research map / Detection and segmentation / 3D detection and driving
Monocular 3D Object Detection for Autonomous Driving
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 |
|---|---|---|---|
| Use monocular 3D proposals scored with semantic, context, shape, and location features, followed by CNN scoring | KITTI object detection · KITTI test Car, easy/moderate/hard | AP (%): 86.71 -> 92.33; 81.84 -> 88.66; 71.12 -> 78.96 | Helped |
| Use monocular 3D proposals scored with semantic, context, shape, and location features, followed by CNN scoring | KITTI object detection · KITTI test Pedestrian, easy/moderate/hard | AP (%): 78.86 -> 80.35; 65.90 -> 66.68; 61.18 -> 63.44 | Helped |
| Use monocular 3D proposals scored with semantic, context, shape, and location features, followed by CNN scoring | KITTI object detection · KITTI test Cyclist, easy/moderate/hard | AP (%): 72.26 -> 76.04; 63.35 -> 66.36; 55.90 -> 58.87 | Helped |
| Add class semantic features to the location prior (ablation) | Monocular 3D proposal model · KITTI validation Car moderate | average recall (AR): 31.2 -> 44.2 | Helped |
| Add context features to class semantics and location prior (ablation) | Monocular 3D proposal model · KITTI validation Car moderate | average recall (AR): 44.2 -> 53.4 | Helped |
| Add shape features to context, class semantics, and location prior (ablation) | Monocular 3D proposal model · KITTI validation Car moderate | average recall (AR): 53.4 -> 59 | Helped |
| Add instance semantic features to the model with shape, context, class semantics, and location prior (ablation) | Monocular 3D proposal model · KITTI validation Car moderate | average recall (AR): 59 -> 59.9 | Helped |
Closest papers by meaning
- MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships (CVPR 2020 · similarity 0.90)
- Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction (CVPR 2019 · similarity 0.90)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.88)
- Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · similarity 0.88)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.88)
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 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.