Beyond Endpoints: Path-Centric Reasoning for Vectorized Off-Road Network Extraction

TL;DR

This paper introduces WildRoad, a new off-road road network dataset, and MaGRoad, a path-centric model that improves robustness and speed in off-road road extraction, addressing limitations of previous node-centric approaches.

Contribution

The paper presents a novel off-road road dataset and a path-centric extraction framework that enhances robustness and efficiency over existing methods.

Findings

MaGRoad achieves state-of-the-art performance on WildRoad.

MaGRoad is approximately 2.5 times faster in inference.

The dataset and method generalize well to urban environments.

Abstract

Deep learning has advanced vectorized road extraction in urban settings, yet off-road environments remain underexplored and challenging. A significant domain gap causes advanced models to fail in wild terrains due to two key issues: lack of large-scale vectorized datasets and structural weakness in prevailing methods. Models such as SAM-Road employ a node-centric paradigm that reasons at sparse endpoints, making them fragile to occlusions and ambiguous junctions in off-road scenes, leading to topological errors. This work addresses these limitations in two complementary ways. First, we release WildRoad, a global off-road road network dataset constructed efficiently with a dedicated interactive annotation tool tailored for road-network labeling. Second, we introduce MaGRoad (Mask-aware Geodesic Road network extractor), a path-centric framework that aggregates multi-scale visual evidence along candidate paths to infer connectivity robustly. Extensive experiments show that MaGRoad achieves state-of-the-art performance on our challenging WildRoad benchmark while generalizing well to urban datasets. An efficient vertex extraction strategy also yields roughly 2.5X faster inference, improving practical applicability. Together, the dataset and path-centric paradigm provide a stronger foundation for mapping roads in the wild. We release both the dataset and code at this repository. We release both the dataset and code at https://github.com/xiaofei-guan/MaGRoad.