Research map / Detection and segmentation / CNN features
PriorMaskMap: Robust Online Vectorized Map Construction with Biased Priors
Haoming Xu, Wei Li, Yu Hu
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 vectorized prior in DPQG on top of SCP and CRM (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 74.8 -> 76.7 | Improved |
| add DPQG (vectorized prior) with no SCP or CRM (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 71.4 -> 75.8 | Improved |
| add CRM to DPQG-only (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 75.8 -> 76.5 | Improved |
| add SCP to DPQG-only (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 75.8 -> 76.4 | Improved |
| add SCP to DPQG+CRM (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 76.5 -> 76.7 | Improved |
| add CRM to DPQG+SCP (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 76.4 -> 76.7 | Improved |
| add SCP and CRM without vectorized prior (ablation) | PriorMaskMap · nuScenes val (rotation bias, ablation) | mAP: 71.4 -> 74.8 | Improved |
| PriorMaskMap vs HRMapNet† on mixed biased prior, 24 epochs | HRMapNet† · nuScenes val (mixed biased prior) | mAP: 79.7 -> 81.4 | Improved |
| PriorMaskMap vs HRMapNet† with longer training, 110 epochs | HRMapNet† · nuScenes val (mixed biased prior) | mAP: 83.4 -> 85.0 | Improved |
| PriorMaskMap vs HRMapNet† under lane widening bias | HRMapNet† · nuScenes val (lane widening bias) | mAP: 75.3 -> 79.0 | Improved |
| PriorMaskMap vs HRMapNet† under lane narrowing bias | HRMapNet† · nuScenes val (lane narrowing bias) | mAP: 76.2 -> 78.9 | Improved |
| PriorMaskMap vs HRMapNet† under lane addition bias | HRMapNet† · nuScenes val (lane addition bias) | mAP: 71.6 -> 72.2 | Improved |
Closest papers by meaning
- PriorDrive: Enhancing Online HD Mapping with Unified Vector Priors (AAAI 2026 · similarity 0.90)
- MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction (CVPR 2024 · similarity 0.87)
- Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction (CVPR 2025 · similarity 0.86)
- SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction (NeurIPS 2025 · similarity 0.86)
- Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation (NeurIPS 2024 · similarity 0.85)
- MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert (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.
