# MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction

arXiv: https://arxiv.org/abs/2306.10301 · HTML: https://mlsanity.com/paper/2306.10301/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 17 Jun 2023.

## Builds on (most cited first, 10 of 10)

- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve](https://mlsanity.com/paper/2306.09700/) (2023)
- [Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception](https://mlsanity.com/paper/2303.05970/) (2023)

## Built on by (most cited first, 17 of 17)

- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping](https://mlsanity.com/paper/2403.15951/) (2024)
- [MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert](https://mlsanity.com/paper/2412.12704/) (2024)
- [DiffMap: Enhancing Map Segmentation with Map Prior Using Diffusion Model](https://mlsanity.com/paper/2405.02008/) (2024)
- [TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior](https://mlsanity.com/paper/2411.14751/) (2024)
- [MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction](https://mlsanity.com/paper/2410.07733/) (2024)
- [DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation](https://mlsanity.com/paper/2406.14255/) (2024)
- [TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem](https://mlsanity.com/paper/2409.11325/) (2024)
- [Spatial Retrieval Augmented Autonomous Driving](https://mlsanity.com/paper/2512.06865/) (2025)
- [LGmap: Local-to-Global Mapping Network for Online Long-Range Vectorized HD Map Construction](https://mlsanity.com/paper/2406.13988/) (2024)
- [CAMAv2: A Vision-Centric Approach for Static Map Element Annotation](https://mlsanity.com/paper/2407.21331/) (2024)
- [HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning](https://mlsanity.com/paper/2411.01408/) (2024)
- [An Overview about Emerging Technologies of Autonomous Driving](https://mlsanity.com/paper/2306.13302/) (2023)
- [Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection](https://mlsanity.com/paper/2503.06237/) (2025)
- [SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Prediction](https://mlsanity.com/paper/2602.21589/) (2026)
- [SuperMapNet for Long-Range and High-Accuracy Vectorized HD Map Construction](https://mlsanity.com/paper/2505.13856/) (2025)
- [Addressing Diverging Training Costs using BEVRestore for High-resolution Bird's Eye View Map Construction](https://mlsanity.com/paper/2405.01016/) (2024)

## Abstract (arXiv)

This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction. By delving into the vectorization pipeline, we elaborate an effective architecture, termed as MachMap, which formulates the task of HD-map construction as the point detection paradigm in the bird-eye-view space with an end-to-end manner. Firstly, we introduce a novel map-compaction scheme into our framework, leading to reducing the number of vectorized points by 93% without any expression performance degradation. Build upon the above process, we then follow the general query-based paradigm and propose a strong baseline with integrating a powerful CNN-based backbone like InternImage, a temporal-based instance decoder and a well-designed point-mask coupling head. Additionally, an extra optional ensemble stage is utilized to refine model predictions for better performance. Our MachMap-tiny with IN-1K initialization achieves a mAP of 79.1 on the Argoverse2 benchmark and the further improved MachMap-huge reaches the best mAP of 83.5, outperforming all the other online HD-map construction approaches on the final leaderboard with a distinct performance margin (> 9.8 mAP at least).