# MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction

arXiv: https://arxiv.org/abs/2410.07733 · HTML: https://mlsanity.com/paper/2410.07733/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 41 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction](https://mlsanity.com/paper/2308.12570/) (2023)
- [PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark](https://mlsanity.com/paper/2203.11089/) (2022)
- [Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection](https://mlsanity.com/paper/2010.12035/) (2020)
- [Multimodal End-to-End Autonomous Driving](https://mlsanity.com/paper/1906.03199/) (2019)
- [PolyLaneNet: Lane Estimation via Deep Polynomial Regression](https://mlsanity.com/paper/2004.10924/) (2020)
- [PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction](https://mlsanity.com/paper/2308.16477/) (2023)
- [CLRNet: Cross Layer Refinement Network for Lane Detection](https://mlsanity.com/paper/2203.10350/) (2022)
- [End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve](https://mlsanity.com/paper/2306.09700/) (2023)
- [Neural Map Prior for Autonomous Driving](https://mlsanity.com/paper/2304.08481/) (2023)
- [LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving](https://mlsanity.com/paper/2312.16108/) (2023)

## Built on by (most cited first, 9 of 9)

- [HisTrackMap: Global Vectorized High-Definition Map Construction via History Map Tracking](https://mlsanity.com/paper/2503.07168/) (2025)
- [Uni-PrevPredMap: Extending PrevPredMap to a Unified Framework of Prior-Informed Modeling for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2504.06647/) (2025)
- [Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction](https://mlsanity.com/paper/2503.23109/) (2025)
- [MapFM: Foundation Model-Driven HD Mapping with Multi-Task Contextual Learning](https://mlsanity.com/paper/2506.15313/) (2025)
- [RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors](https://mlsanity.com/paper/2507.21567/) (2025)
- [SuperMapNet for Long-Range and High-Accuracy Vectorized HD Map Construction](https://mlsanity.com/paper/2505.13856/) (2025)
- [ArgoTweak: Towards Self-Updating HD Maps through Structured Priors](https://mlsanity.com/paper/2509.08764/) (2025)
- [PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction](https://mlsanity.com/paper/2602.16669/) (2026)
- [GSMap: 2D Gaussians for Online HD Mapping](https://mlsanity.com/paper/2605.09619/) (2026)

## Abstract (arXiv)

The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements. Current state-of-the-art methods often adopt solely either point-level or instance-level representation, overlooking the strong intrinsic relationships between points and instances. In this work, we propose a simple yet efficient framework named MGMapNet (Multi-Granularity Map Network) to model map element with a multi-granularity representation, integrating both coarse-grained instance-level and fine-grained point-level queries. Specifically, these two granularities of queries are generated from the multi-scale bird's eye view (BEV) features using a proposed Multi-Granularity Aggregator. In this module, instance-level query aggregates features over the entire scope covered by an instance, and the point-level query aggregates features locally. Furthermore, a Point Instance Interaction module is designed to encourage information exchange between instance-level and point-level queries. Experimental results demonstrate that the proposed MGMapNet achieves state-of-the-art performance, surpassing MapTRv2 by 5.3 mAP on nuScenes and 4.4 mAP on Argoverse2 respectively.