Research map / Label-efficient and robust learning / Recognition and long-tail
RTMap: Real-Time Recursive Mapping with Change Detection and Localization
Yuheng Du, Sheng Yang, Lingxuan Wang, Zhenghua Hou, Chengying Cai, Zhitao Tan, Mingxia Chen, Shi-Sheng Huang, Qiang Li
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 probabilistic vertex density U (ablation) | RTMap cycle 3 · TbV straight | mAP avg: 50.7 -> 57.6 | Improved |
| add probabilistic vertex density U (ablation) | RTMap cycle 2 · TbV straight | mAP avg: 40.2 -> 45.6 | Improved |
| add probabilistic vertex density U (ablation) | RTMap cycle 3 · TbV turning | mAP avg: 46.5 -> 55.4 | Improved |
| add probabilistic vertex density U (ablation) | RTMap cycle 2 · TbV turning | mAP avg: 41.9 -> 45.5 | Improved |
| add more crowdsourcing cycles (2 to 3) | RTMap · TbV straight | mAP avg: 45.6 -> 57.6 | Improved |
| use RTMap crowdsourcing instead of MapTracker averaging | MapTracker · TbV turning | mAP avg: 28.0 -> 55.4 | Improved |
| add change detection by separating Q_map from Q_prior (ablation) | RTMap · TbV localization | lateral error mean (m): 0.163 -> 0.125 | Improved |
| add change detection by separating Q_map from Q_prior (ablation) | RTMap · TbV localization | yaw error mean (deg): 0.332 -> 0.317 | Improved |
| use optimization-based pose T^R instead of end-to-end T^E (ablation) | RTMap · nuScenes localization | yaw error mean (deg): 0.521 -> 0.368 | Improved |
| use optimization-based pose T^R instead of end-to-end T^E (ablation) | RTMap · nuScenes localization | lateral error mean (m): 0.142 -> 0.121 | Improved |
| add localization loss L_pose (ablation) | RTMap T^R · nuScenes localization | longitudinal error 90th (m): 1.510 -> 1.436 | Improved |
| add vertex regression loss L_pts (ablation) | RTMap T^R · nuScenes localization | lateral error mean (m): 0.122 -> 0.118 | Improved |
Closest papers by meaning
- InteractionMap: Improving Online Vectorized HDMap Construction with Interaction (CVPR 2025 · similarity 0.86)
- Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation (NeurIPS 2024 · similarity 0.86)
- MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert (AAAI 2025 · similarity 0.85)
- Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping (NeurIPS 2026 · similarity 0.85)
- SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction (NeurIPS 2025 · similarity 0.85)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · 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.
