AI 中文总结
提出PolyTopoBench基准，评估遥感图像中带孔洞复杂矢量多边形生成，发现现有方法在简单轮廓上有效但复杂拓扑上性能下降，强调拓扑感知设计。
AI 中文摘要
矢量多边形生成将视觉输入（例如遥感（RS）图像）转换为矢量化的多边形几何体，支持自动驾驶、矢量地图构建和遥感等应用。早期流程预测栅格掩码并将其后处理为多边形，这阻碍了端到端优化，并且可能遗漏小物体或引入不准确的顶点。近期方法直接生成矢量多边形，但大多数专注于简单的外轮廓，它们要么无法表示带孔洞的复杂多边形，要么无法保持其拓扑结构。在本文中，我们提出了PolyTopoBench，一个用于从遥感图像生成矢量多边形的统一评估框架，明确强调复杂多边形。PolyTopoBench评估外环和内环，并在两个覆盖建筑物、道路、植被和非植被区域的遥感图像数据集上，对11种代表性方法进行基准测试，包括基于分割的多边形化流程、视觉基础模型基线和专门的矢量多边形生成器。实验表明，现有方法通常能恢复简单的外边界，但在处理带孔洞或多环的多边形时性能显著下降。这些结果揭示了复杂多边形生成是一个尚未解决的挑战，并激励了拓扑感知的基准和模型设计。代码和数据可在该https URL获取。
英文摘要
Vector polygon generation converts visual inputs, e.g., remote sensing (RS) images, into vectorized polygonal geometries, supporting applications such as autonomous driving, vector map construction, and remote sensing. Early pipelines predict raster masks and post-process them into polygons, which prevents end-to-end optimization and may miss small objects or introduce inaccurate vertices. Recent methods directly generate vector polygons, but most focus on simple exterior contours, while they either cannot represent complex polygons with holes or fail to preserve their topology. In this paper, we propose PolyTopoBench, a unified evaluation framework for vector polygon generation from RS images with explicit emphasis on complex polygons. PolyTopoBench evaluates both exterior and interior rings, and benchmarks 11 representative methods, including segmentation-based polygonization pipelines, vision foundation model baselines, and specialized vector polygon generators, on two RS-image datasets covering buildings, roads, vegetation, and unvegetated regions. Experiments show that existing methods often recover simple exterior boundaries but degrade substantially on polygons with holes or multiple rings. These results reveal complex polygon generation as an unresolved challenge and motivate topology-aware benchmarks and model designs. Code and data are available at https://github.com/seai-lab/PolyTopoBench.
CommentsAccepted by NeurIPS 2026 (Evaluations and Datasets Track)
