Polygonal building outline extraction has been a research focus in recent years. Most existing methods have addressed this challenging task by decomposing it into several subtasks and employing carefully designed architectures. Despite their accuracy, such pipelines often introduce inefficiencies during training and inference. This paper presents an end-to-end framework, denoted as PolyR-CNN, which offers an efficient and fully integrated approach to predict vectorized building polygons and bounding boxes directly from remotely sensed images. Notably, PolyR-CNN leverages solely the features of the Region of Interest (RoI) for the prediction, thereby mitigating the necessity for complex designs. Furthermore, we propose a novel scheme with PolyR-CNN to extract detailed outline information from polygon vertex coordinates, termed vertex proposal feature, to guide the RoI features to predict more regular buildings. PolyR-CNN demonstrates the capacity to deal with buildings with holes through a simple post-processing method on the Inria dataset. Comprehensive experiments conducted on the CrowdAI dataset show that PolyR-CNN achieves competitive accuracy compared to state-of-the-art methods while significantly improving computational efficiency, i.e., achieving 79.2 Average Precision (AP), exhibiting a 15.9 AP gain and operating 2.5 times faster and four times lighter than the well-established end-to-end method PolyWorld. Replacing the backbone with a simple ResNet-50, PolyR-CNN maintains a 71.1 AP while running four times faster than PolyWorld. The code is available at: https://github.com/HeinzJiao/PolyR-CNN.

中文翻译：

---

PolyR-CNN： R-CNN 用于端到端多边形建筑物轮廓提取


多边形建筑轮廓提取是近年来的研究热点。大多数现有方法都通过将其分解为几个子任务并采用精心设计的架构来解决这一具有挑战性的任务。尽管它们很准确，但此类管道通常会在训练和推理期间导致效率低下。本文提出了一个端到端框架，表示为 PolyR-CNN，它提供了一种高效且完全集成的方法，可以直接从遥感图像中预测矢量化建筑多边形和边界框。值得注意的是，PolyR-CNN 仅利用感兴趣区域 （RoI） 的特征进行预测，从而减少了复杂设计的必要性。此外，我们提出了一种基于 PolyR-CNN 的新方案，从多边形顶点坐标中提取详细的轮廓信息，称为顶点建议特征，以指导 RoI 特征预测更多规则建筑物。PolyR-CNN 通过在 Inria 数据集上通过简单的后处理方法展示了处理有孔建筑物的能力。在 CrowdAI 数据集上进行的综合实验表明，与最先进的方法相比，PolyR-CNN 实现了具有竞争力的精度，同时显著提高了计算效率，即达到 79.2 的平均精度 （AP），AP 增益为 15.9，运行速度比成熟的端到端方法 PolyWorld 快 2.5 倍，重量轻 4 倍。PolyR-CNN 用简单的 ResNet-50 取代了主干网，保持了 71.1 接入点，同时运行速度是 PolyWorld 的四倍。该代码可在以下网址获得：https://github.com/HeinzJiao/PolyR-CNN。