UniBuild：基于细节解码与几何正则化的多源光学遥感影像统一建筑物制图

中文摘要 AI 辅助

从光学遥感（RS）影像中提取建筑物是城市制图的基础，然而现有方法往往针对特定数据集，且对未见领域的泛化能力较差。其实际应用还受到细节恢复不足和几何正则化较弱的限制，导致边界模糊、形状不规则以及相邻建筑物合并等问题。为解决这些问题，我们提出了UniBuild，一个面向多源RGB光学遥感影像的统一建筑物提取框架。首先，构建了一个在异构RGB光学数据集上的统一多数据集训练方案，以学习跨传感器和分辨率的可迁移建筑物表征。其次，设计了一种新颖的保留细节的HR-DPT解码器，将高层语义特征与高分辨率空间特征相结合，以增强建筑物细节恢复。第三，通过基于结构张量的方向感知损失引入几何感知正则化，以实现边界方向一致性，并采用鞍点感知损失来抑制低分辨率条件下狭窄建筑间隙中的虚假激活。我们在多源RGB光学数据集上训练和评估UniBuild，包括10个公开的高分辨率数据集和两个自采集的低分辨率数据集。实验表明，UniBuild在不同数据集上持续提升了建筑物区域精度、边界清晰度和相邻建筑物分离效果。它还对未见领域具有良好的泛化能力，并支持高达10米分辨率的RGB光学遥感影像的实际建筑物提取。预测的掩码可通过简单的多边形化进一步转换为兼容GIS的建筑物足迹。训练好的模型和推理代码已在此https URL发布。

英文摘要

Building extraction from optical remote sensing (RS) imagery is fundamental to urban mapping, yet existing methods are often dataset-specific and generalize poorly to unseen domains. Their practical use is also limited by insufficient detail recovery and weak geometric regularization, leading to blurred boundaries, irregular shapes, and merged adjacent buildings. To address these issues, we propose UniBuild, a unified building extraction framework for multi-source RGB optical RS imagery. First, a unified multi-dataset training scheme is constructed over heterogeneous RGB optical datasets to learn transferable building representations across sensors and resolutions. Second, a novel detail-preserving HR-DPT decoder is designed to integrate high-level semantic features with high-resolution spatial features, enhancing building detail recovery. Third, geometry-aware regularization is introduced through a structure-tensor-based direction-aware loss for boundary direction consistency and a saddle-aware loss for suppressing false activations in narrow inter-building gaps under low-resolution conditions. We train and evaluate UniBuild on multi-source RGB optical datasets, including 10 public high-resolution datasets and two self-collected low-resolution datasets. Experiments show that UniBuild consistently improves building-region accuracy, boundary sharpness, and adjacent-building separation across diverse datasets. It also generalizes well to unseen domains and supports practical building extraction from RGB optical RS imagery up to 10\,m resolution. The predicted masks can be further converted into GIS-compatible building footprints through simple polygonization. The trained model and inference code are released at https://github.com/zhu-xlab/UniBuild.

发表机构

• Technical University of Munich（慕尼黑工业大学）
• Munich Center for Machine Learning（慕尼黑机器学习中心）

机构由 AI 辅助整理，请以论文原文为准。