Research map / Detection and segmentation / CNN features
Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks
Sehwan Choi, Jun Won Choi, Jungho Kim, Hongjae Shin
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 IMPNet with Mask-Aware Queries to the baseline (ablation) | Mask2Map baseline · nuScenes ablation | mAP: 39.4 -> 45.3 | Improved |
| add MMPNet (PQG and GFE) on top of IMPNet (ablation) | Mask2Map · nuScenes ablation | mAP: 45.3 -> 49.1 | Improved |
| add Inter-network Denoising Training (ablation) | Mask2Map · nuScenes ablation | mAP: 49.1 -> 55.6 | Improved |
| add denoising training to raise query matching consistency (ablation) | Mask2Map · nuScenes ablation | Query Utilization (%): 24.7 -> 74.7 | Improved |
| add Positional Query Generator (ablation) | MMPNet · nuScenes ablation | mAP: 50.8 -> 54.2 | Improved |
| add Geometric Feature Extractor (ablation) | MMPNet · nuScenes ablation | mAP: 50.8 -> 53.9 | Improved |
| combine PQG and GFE (ablation) | MMPNet · nuScenes ablation | mAP: 50.8 -> 55.6 | Improved |
| add Map Noise to GT segmentation masks (ablation) | Inter-network Denoising Training · nuScenes ablation | mAP: 54.8 -> 55.6 | Improved |
| add Max Survival sampling in GFE (ablation) | GFE · nuScenes ablation | mAP: 55.0 -> 55.6 | Improved |
| increase GFE sampling points Ns from 20 to 40 (ablation) | GFE · nuScenes ablation | mAP: 55.6 -> 54.8 | Hurt |
| use Mask2Map instead of MapTRv2 | nuScenes camera R50 24 epochs · nuScenes val | FPS: 14.1 -> 10.1 | Hurt |
Later papers that compared with this method
1 later accepted paper reports Mask2Map as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DAMap: Distance-aware MapNet for High Quality HD Map Construction (ICCV 2025 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction (CVPR 2024 · similarity 0.89)
- MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert (AAAI 2025 · similarity 0.88)
- Improving Bird's Eye View Semantic Segmentation by Task Decomposition (CVPR 2024 · similarity 0.88)
- Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation (NeurIPS 2024 · similarity 0.87)
- VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization (NeurIPS 2024 · similarity 0.86)
- Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets (NeurIPS 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.
