Pith. sign in

REVIEW 4 cited by

Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.16733 v1 pith:MSXCWAXA submitted 2024-11-23 cs.CV

Pan Yin , Kaiyu Li , Xiangyong Cao , Jing Yao , Lei Liu , Xueru Bai , Feng Zhou , Deyu Meng This is my paper
classification cs.CV
keywords roaddatasetextractionglobal-scalegraphsam-roadmethodissue
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Recently, road graph extraction has garnered increasing attention due to its crucial role in autonomous driving, navigation, etc. However, accurately and efficiently extracting road graphs remains a persistent challenge, primarily due to the severe scarcity of labeled data. To address this limitation, we collect a global-scale satellite road graph extraction dataset, i.e. Global-Scale dataset. Specifically, the Global-Scale dataset is $\sim20 \times$ larger than the largest existing public road extraction dataset and spans over 13,800 $km^2$ globally. Additionally, we develop a novel road graph extraction model, i.e. SAM-Road++, which adopts a node-guided resampling method to alleviate the mismatch issue between training and inference in SAM-Road, a pioneering state-of-the-art road graph extraction model. Furthermore, we propose a simple yet effective ``extended-line'' strategy in SAM-Road++ to mitigate the occlusion issue on the road. Extensive experiments demonstrate the validity of the collected Global-Scale dataset and the proposed SAM-Road++ method, particularly highlighting its superior predictive power in unseen regions. The dataset and code are available at \url{https://github.com/earth-insights/samroadplus}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    PathPainter transfers image generation models to embodied navigation by generating traversability masks from BEV images and language instructions while using cross-view localization to reduce odometry drift.

  2. IRSAMap:Towards Large-Scale, High-Resolution Land Cover Map Vectorization

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    A new global remote sensing dataset with 1.8 million vector-annotated instances across 10 land cover classes, spanning 79 regions on six continents, for benchmarking vector-based land cover mapping.

  3. RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Introduces the largest global aerial road segmentation dataset and RoadGIE, an interactive model using topology-aware prompts that reports SOTA accuracy and connectivity on the new benchmark with a 3.7M parameter network.

  4. PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation

    cs.RO 2026-05 unverdicted novelty 5.0 of 10

    Navigation system transfers image generation models to embodied tasks via BEV-based traversability mask generation from language and cross-view localization for odometry correction, shown on a UAV completing 160m outd...

Pith tools