PolyGeom: Geometry-Aware Graph Transformer for Building Polygon Extraction in Remote Sensing Images
Year: 2026
Type: article
Abstract: Building polygon extraction is a critical task in remote sensing analysis and a fundamental component of modern urban management. Conventional segmentation-based methods often suffer from geometric distortions during the conversion from masks to polygons. End-to-end polygon prediction approaches (e.g., PolyWorld) alleviate this issue by directly predicting building polygons; however, existing PolyWorld-like methods remain limited in accurate corner vertex detection and polygon reasoning due to insufficient representation learning, particularly for geometry. In this work, we propose PolyGeom, an end-to-end framework equipped with a geometry-aware graph transformer for accurate and robust building polygon extraction. PolyGeom employs the Segment Anything Model (SAM) as its backbone to leverage large-scale pretrained features, thereby capturing both local and global semantics. Moreover, we propose a geometry-aware graph transformer that explicitly models geometry of building polygons, facilitating more reliable polygon reasoning. Extensive experiments on three challenging benchmarks, CrowdAI, WHU, and BONAI datasets, demonstrate that PolyGeom consistently outperforms existing methods in terms of building detection accuracy, topology correctness, and geometry alignment. Ablation studies further validate the effectiveness of the two key proposed designs in building polygon extraction.
Source: Remote Sensing
DOI: 10.3390/rs18040551
Authors: Hongbin Pei, Huiyuan Li, Xufan Hou, Bo Yang, Huiqi Deng
Language: English
Subfield: Ocean Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,258
Awards: G3061547681, G4397188778, G4799629975
OpenAlex ID: W7128429828