Research map / Detection and segmentation / 3D detection and driving
Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving
Peiliang Li, Tong Qin, andShaojie Shen
Read the paperCheck 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 feature observation to semantic measurement (ablation) | semantic 3D object tracking · KITTI tracking, easy objects | AP_bv IoU 0.25: 63.12 -> 76.23 | Improved |
| add motion model to semantic measurement (ablation) | semantic 3D object tracking · KITTI tracking, hard objects | AP_bv IoU 0.25: 53.18 -> 58.84 | Improved |
| add motion model to semantic plus feature (ablation) | semantic 3D object tracking · KITTI tracking, hard objects | AP_bv IoU 0.25: 66.18 -> 70.85 | Improved |
| add motion model to semantic plus feature (ablation) | semantic 3D object tracking · KITTI tracking, easy objects | AP_bv IoU 0.5: 48.82 -> 46.96 | Hurt |
| add point cloud alignment to S+F+M (ablation) | semantic 3D object tracking · KITTI tracking, easy objects | AP_bv IoU 0.25: 77.87 -> 88.07 | Improved |
| add point cloud alignment to S+F+M (ablation) | semantic 3D object tracking · KITTI tracking, easy objects | AP_3d IoU 0.5: 40.50 -> 48.51 | Improved |
| add point cloud alignment to S+F+M (ablation) | semantic 3D object tracking · KITTI tracking, hard objects | AP_3d IoU 0.5: 34.59 -> 34.54 | No clear effect |
| add feature observation to semantic measurement (ablation) | semantic 3D object tracking · KITTI tracking | runtime (ms): 120 -> 170 | Hurt |
| add motion model to semantic measurement (ablation) | semantic 3D object tracking · KITTI tracking | runtime (ms): 120 -> 121 | No clear effect |
| full system versus 3DOP stereo detector | S+F+M+P · KITTI tracking, easy objects | AP_3d IoU 0.5: 53.73 vs 48.51 | Hurt |
| full system versus 3DOP stereo detector | S+F+M+P · KITTI tracking, easy objects | AP_bv IoU 0.25: 81.34 -> 88.07 | Improved |
| full system versus 3DOP stereo detector | S+F+M+P · KITTI tracking | runtime (ms): 1200 -> 173 | Improved |
Closest papers by meaning
- R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras (ICCV 2023 · similarity 0.87)
- IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving (CVPR 2020 · similarity 0.86)
- Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving (CVPR 2022 · similarity 0.86)
- 3D Object Detection for Autonomous Driving: A Comprehensive Survey (IJCV 2023 · similarity 0.86)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 2025 · similarity 0.85)
- Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement (AAAI 2025 · similarity 0.85)
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.
