# DeH4R: A Decoupled and Hybrid Method for Road Network Graph Extraction

arXiv: https://arxiv.org/abs/2508.13669 · HTML: https://mlsanity.com/paper/2508.13669/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model](https://mlsanity.com/paper/2306.16269/) (2023)
- [SpaceNet: A Remote Sensing Dataset and Challenge Series](https://mlsanity.com/paper/1807.01232/) (2018)
- [RoadTracer: Automatic Extraction of Road Networks from Aerial Images](https://mlsanity.com/paper/1802.03680/) (2018)
- [Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images](https://mlsanity.com/paper/2110.01997/) (2021)
- [Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions](https://mlsanity.com/paper/2401.03495/) (2024)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [Topological Map Extraction from Overhead Images](https://mlsanity.com/paper/1812.01497/) (2018)
- [Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding](https://mlsanity.com/paper/2007.09547/) (2020)
- [HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction](https://mlsanity.com/paper/2403.08639/) (2024)
- [Segment Anything Model for Road Network Graph Extraction](https://mlsanity.com/paper/2403.16051/) (2024)
- [RNGDet: Road Network Graph Detection by Transformer in Aerial Images](https://mlsanity.com/paper/2202.07824/) (2022)
- [RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement](https://mlsanity.com/paper/2209.10150/) (2022)
- [Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images](https://mlsanity.com/paper/2010.13106/) (2020)
- [csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps](https://mlsanity.com/paper/2111.06020/) (2021)
- [Mastering Spatial Graph Prediction of Road Networks](https://mlsanity.com/paper/2210.00828/) (2022)

## Abstract (arXiv)

The automated extraction of complete and precise road network graphs from remote sensing imagery remains a critical challenge in geospatial computer vision. Segmentation-based approaches, while effective in pixel-level recognition, struggle to maintain topology fidelity after vectorization postprocessing. Graph-growing methods build more topologically faithful graphs but suffer from computationally prohibitive iterative ROI cropping. Graph-generating methods first predict global static candidate road network vertices, and then infer possible edges between vertices. They achieve fast topology-aware inference, but limits the dynamic insertion of vertices. To address these challenges, we propose DeH4R, a novel hybrid model that combines graph-generating efficiency and graph-growing dynamics. This is achieved by decoupling the task into candidate vertex detection, adjacent vertex prediction, initial graph contruction, and graph expansion. This architectural innovation enables dynamic vertex (edge) insertions while retaining fast inference speed and enhancing both topology fidelity and spatial consistency. Comprehensive evaluations on CityScale and SpaceNet benchmarks demonstrate state-of-the-art (SOTA) performance. DeH4R outperforms the prior SOTA graph-growing method RNGDet++ by 4.62 APLS and 10.18 IoU on CityScale, while being approximately 10 × faster. The code will be made publicly available at https://github.com/7777777FAN/DeH4R.