More accurate extraction of invisible building footprints from very-high-resolution (VHR) aerial images relies on roof segmentation and roof-to-footprint offset extraction. Existing state-of-the-art methods based on instance segmentation suffer from poor generalization when extended to large-scale data production and fail to achieve low-cost human interactive annotation. The latest prompt paradigms inspire us to design a promptable framework for roof and offset extraction, which transforms end-to-end algorithms into promptable methods. Within this framework, we propose a novel Offset-Building Model (OBM). To rigorously evaluate the algorithm's capabilities, we introduce a prompt-based evaluation method, where our model reduces offset errors by 16.6% and improves roof Intersection over Union (IoU) by 10.8% compared to other models. Leveraging the common patterns in predicting offsets, we propose Distance-NMS (DNMS) algorithms, enabling the model to further reduce offset vector loss by 6.5%. To further validate the generalization of models, we tested them using a new dataset with over 7,000 manually annotated instance samples. Our algorithms and dataset are available at https://anonymous.4open.science/r/OBM-B3EC.

翻译：摘要：从超高分辨率（VHR）航拍图像中更精确地提取不可见建筑足迹，依赖于屋顶分割及屋顶到足迹的偏移量提取。现有基于实例分割的最先进方法在扩展至大规模数据生产时泛化能力差，且难以实现低成本人工交互标注。最新的提示范式启发我们设计一种可提示的屋顶与偏移量提取框架，将端到端算法转化为提示式方法。在该框架内，我们提出了一种新颖的偏移建筑模型（OBM）。为严格评估算法能力，我们引入基于提示的评估方法，结果表明我们的模型相比其他模型将偏移误差降低了16.6%，并将屋顶交并比（IoU）提升了10.8%。利用偏移预测中的常见模式，我们提出距离非极大值抑制（DNMS）算法，使模型进一步将偏移矢量损失降低6.5%。为验证模型泛化能力，我们使用包含超过7000个手动标注实例样本的新数据集进行了测试。我们的算法与数据集可通过https://anonymous.4open.science/r/OBM-B3EC获取。