发表机构
Texas A&M University（德克萨斯A&M大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文通过挖掘单视角模型间的冲突样本，提出可见性条件可靠性门控，在灾害损毁评估中动态选择可信视角，显著优于对称融合方法。
AI 中文摘要
灾害发生后，建筑物损毁评估通常基于俯视瓦片图像和地面拍摄照片，大多数方法对称地融合这两种视角，对每栋建筑给予同等信任。本文聚焦于这一假设失效的样本：冲突案例，即两个独立训练的单视角模型在这些样本上产生分歧。我们从三个配对数据集中挖掘此类案例（2025年伊顿野火的检查照片，以及飓风伊恩和米尔顿的街景全景图，每个均与极高分辨率俯视瓦片图像匹配），这些冲突案例占数据的10%-33%。在这些样本上，一个简单信任正确视角的预言机在准确率上比我们测试的所有融合方法高出0.37-0.41，且该差距在更长的训练、校准和骨干网络变化下依然存在。我们通过一个可见性条件可靠性门控部分恢复该差距：该线性模型基于建筑可见性特征、逐视角校准置信度以及分歧本身来决定信任哪个视角。在野火数据上，该门控是唯一显著优于校准概率平均（冲突上+0.051，p=0.0001）和端到端融合（+0.072，p<10^-4）的方法；在全景数据集上，其表现与这些方法相当。一个受控的视场实验解释了原因：将全景图裁剪至建筑区域使融合收益翻倍，而相同尺寸的随机裁剪则无此效果。最后，冲突的空间密度无需标签即可预测瓦片级损毁（Spearman r=0.615，p=0.001）。挖掘冲突将“融合是否有帮助？”转变为“哪个视角应被信任，在何处，以及为何？”。
英文摘要
After a disaster, building damage is assessed from overhead tiles and ground-level photographs, and most methods fuse the two views symmetrically, trusting both equally for every building. This paper focuses on the samples where that assumption fails: the conflict cases, on which two independently trained single-view models disagree. We mine such cases from three paired collections (inspection photographs from the 2025 Eaton wildfire and street-view panoramas from Hurricanes Ian and Milton, each matched to very-high-resolution overhead tiles), where they make up 10-33% of the data. On these samples an oracle that simply trusts the correct view beats every fusion method we tested by 0.37-0.41 accuracy, and the gap survives longer training, calibration, and backbone changes. We recover part of it with a visibility-conditioned reliability gate: a linear model that decides which view to trust from building-visibility features, calibrated per-view confidences, and the disagreement itself. On the wildfire data the gate is the only method that significantly beats calibrated probability averaging (+0.051 on conflicts, p=0.0001) and end-to-end fusion (+0.072, p<10^-4); on the panoramic datasets it matches them. A controlled field-of-view experiment explains why: cropping panoramas toward the building doubles the benefit of fusion, whereas random crops of the same size do not. Finally, the spatial density of conflicts predicts tile-level damage without labels (Spearman r=0.615, p=0.001). Mining conflicts turns "does fusion help?" into "which view should be trusted, where, and why?".
Comments4 pages, 3 figures; Accepted for publication in the proceedings of the 5th ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data (GeoSearch '26), held November 3-6, 2026, in Riverside, California, USA
