Research map / Detection and segmentation / 3D detection and driving
Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds
Read the paperCheck 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 |
|---|---|---|---|
| jointly use spatio-temporal detection features, tracklet-aware detection, and SG-GNN | 3D DetecTrack · nuScenes validation | mAP: 49.15 -> 52.89 | Helped |
| jointly use spatio-temporal detection features, tracklet-aware detection, and SG-GNN | 3D DetecTrack · nuScenes validation | sAMOTA (%): 39.48 -> 45.60 | Helped |
| add SG-GNN to the baseline (ablation) | 3D DetecTrack · KITTI valid, Car | sAMOTA (%): 92.15 -> 94.97 | Helped |
| add tracklet-aware RPN (Trk-RPN) (ablation) | 3D DetecTrack · KITTI valid, Car | AP_mod.: 89.37 -> 89.96 | Helped |
| add tracklet-aware RPN (Trk-RPN) (ablation) | 3D DetecTrack · KITTI valid, Car | sAMOTA (%): 94.97 -> 95.56 | Helped |
| add tracklet-aware refinement network (Trk-RefNet) (ablation) | 3D DetecTrack · KITTI valid, Car | AP_mod.: 89.96 -> 90.32 | Helped |
| add tracklet-aware refinement network (Trk-RefNet) (ablation) | 3D DetecTrack · KITTI valid, Car | sAMOTA (%): 95.56 -> 96.02 | Helped |
| add SFANet temporal feature aggregation (ablation) | 3D DetecTrack · KITTI valid, Car | AP_mod.: 90.32 -> 91.01 | Helped |
| add SFANet temporal feature aggregation (ablation) | 3D DetecTrack · KITTI valid, Car | sAMOTA (%): 96.02 -> 96.49 | Helped |
| add rule-based edge pruning to the fully-connected GNN (ablation) | SG-GNN · KITTI valid, Car | sAMOTA (%): 94.02 -> 95.50 | Helped |
| add rule-based edge pruning to the fully-connected GNN (ablation) | SG-GNN · KITTI valid, Car | Runtime (ms): 41 -> 34 | Helped |
| add attention-based edge gating after rule-based pruning (ablation) | SG-GNN · KITTI valid, Car | sAMOTA (%): 95.50 -> 96.49 | Helped |
Closest papers by meaning
- LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing and Spatiotemporal Transformer Attention (CVPR 2020 · similarity 0.88)
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud (CVPR 2020 · similarity 0.87)
- JPV-Net: Joint Point-Voxel Representations for Accurate 3D Object Detection (AAAI 2022 · similarity 0.87)
- Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning (Student Abstract) (AAAI 2025 · similarity 0.86)
- SeMoLi: What Moves Together Belongs Together (CVPR 2024 · similarity 0.86)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.86)
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.