Research map / Detection and segmentation / Tracking
PnPNet: End-to-End Perception and Prediction With Tracking in the Loop
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 |
|---|---|---|---|
| Put online tracking and trajectory-level features in the perception-and-prediction loop | PnPNet · nuScenes cars | ADE (90% TP): 0.75 -> 0.68 | Helped |
| Put online tracking and trajectory-level features in the perception-and-prediction loop | PnPNet · ATG4D vehicles | Max recall@0.1 IoU: 97.5 -> 99.1 | Helped |
| Put online tracking and trajectory-level features in the perception-and-prediction loop | PnPNet · ATG4D pedestrians | FDE (90% TP): 0.60 -> 0.54 | Helped |
| Use the learned discrete-continuous tracker instead of a Kalman-filter tracker | PnPNet tracking · nuScenes car | AMOTA: 76.1% -> 81.5% | Helped |
| Add explicit motion features to the trajectory representation (ablation) | PnPNet · ATG4D vehicles | ADE (90% TP): +6.2% | Helped |
| Add single-object tracking to recover occluded tracks (ablation) | PnPNet · ATG4D vehicles | Max recall@0.1 IoU: -1.7 | Helped |
| Add trajectory rescoring (ablation) | PnPNet · ATG4D vehicles | AP@0.5 IoU: -7.9 | Helped |
| Add trajectory refinement (ablation) | PnPNet · ATG4D vehicles | ADE (90% TP): +4.8% | Helped |
| Add the tracking module (ablation) | PnPNet · ATG4D vehicles | ADE (90% TP): +18% | Helped |
Closest papers by meaning
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- Enhancing End-to-End Autonomous Driving with Latent World Model (ICLR 2025 · similarity 0.87)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.87)
- Motion Forecasting in Continuous Driving (NeurIPS 2024 · similarity 0.87)
- SEPT: Towards Efficient Scene Representation Learning for Motion Prediction (ICLR 2024 · similarity 0.86)
- DualAD: Disentangling the Dynamic and Static World for End-to-End Driving (CVPR 2024 · 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.