GeoFormer：一种轻量级Swin Transformer用于从哨兵影像联合估计建筑物高度和轮廓
GeoFormer: A Lightweight Swin Transformer for Joint Building Height and Footprint Estimation from Sentinel Imagery
AI总结：
本文提出GeoFormer，一种基于Swin Transformer的轻量级多任务学习框架，利用公开的哨兵影像数据在100米网格上联合估计建筑物高度和轮廓，验证了窗口局部注意力优于卷积在场景级建筑参数检索中的有效性。
摘要：
建筑物高度（BH）和轮廓（BF）是气候建模、灾害风险评估和人口制图所需的基本城市形态参数，但全球一致的数据仍然稀缺。本文开发了GeoFormer，一种轻量级Swin Transformer多任务学习框架，仅使用公开的哨兵-1 SAR、哨兵-2多光谱和数字高程模型（DEM）数据，在100米网格上联合估计BH和BF。一种地理块数据分割策略强制在54种形态多样的城市中训练和评估区域之间保持严格的空间独立性。我们设定了代表性的CNN基线（ResNet、UNet、SENet）作为基准，并彻底评估了GeoFormer的预测精度、计算效率和空间可迁移性。结果表明，GeoFormer仅使用0.32M参数实现了BH的RMSE为3.19m，优于最佳CNN基线（UNet）7.5%，表明窗口局部注意力比卷积在场景级建筑参数检索中更有效。系统性消融实验进一步揭示，5x5（500m）感受野最优，DEM对高度估计至关重要，多光谱反射率携带主导预测信号。跨洲转移测试证实在无区域特定微调的情况下，BH的RMSE低于3.5m。所有代码、模型权重和最终全球产品均已公开发布。
英文摘要：
Building height (BH) and footprint (BF) are fundamental urban morphological parameters required by climate modelling, disaster-risk assessment, and population mapping, yet globally consistent data remain scarce. In this work, we develop GeoFormer, a lightweight Swin Transformer-based multi-task learning framework that jointly estimates BH and BF on a 100 m grid using only open-access Sentinel-1 SAR, Sentinel-2 multispectral, and DEM data. A geo-blocked data-splitting strategy enforces strict spatial independence between training and evaluation regions across 54 morphologically diverse cities. We set representative CNN baselines (ResNet, UNet, SENet) as benchmarks and thoroughly evaluate GeoFormer's prediction accuracy, computational efficiency, and spatial transferability. Results show that GeoFormer achieves a BH RMSE of 3.19 m with only 0.32 M parameters -- outperforming the best CNN baseline (UNet) by 7.5% -- indicating that windowed local attention is more effective than convolution for scene-level building-parameter retrieval. Systematic ablation on context window size, model capacity, and input modality further reveals that a 5x5 (500 m) receptive field is optimal, DEM is indispensable for height estimation, and multispectral reflectance carries the dominant predictive signal. Cross-continent transfer tests confirm BH RMSE below 3.5 m without region-specific fine-tuning. All code, model weights, and the resulting global product are publicly released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
