从一张航拍图同时预测屋顶分割与三维几何属性，实现低成本3D建模。
Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery
- 扩展Mask R-CNN，增加属性回归分支并设计条件方位角损失。
- 屋顶坡度误差4度、方位角误差7度、高度误差1米，分割准确率AP50达0.566。
- 适合需要从航拍图重建3D建筑模型的地理信息与城市规划研究者。
本文提出一种方法，从单张航拍正射影像中联合预测实例级屋顶分割掩码及三个连续几何属性——建筑高度、屋顶坡度和屋顶方位角。方法在Mask R-CNN基础上引入专用属性回归分支，并提出两项关键创新：基于条件的方位角损失，对平坦屋顶段抑制监督（因其方位标签本就噪声大）；以及对数归一化高度表示，缓解建筑高度分布严重偏斜的问题。在包含荷兰航拍图像的大规模数据集上训练与评估，该数据集通过3DBAG（全国性基于激光雷达的3D建筑数据集）自动生成真值。采用DINOv3 ConvNeXt-Base主干网络，方法在屋顶坡度上达到约4度的平均绝对误差，方位角为7度，建筑高度为1米，实例分割AP₅₀为0.566。生成的每段掩码与属性足以从单张俯视图像重建简化版3D建筑模型（LoD2），仅需3D参考数据用于训练。
原文摘要 · Abstract (English)
We present a method for jointly predicting instance-level roof segment masks together with three continuous geometric attributes -- building height, roof slope, and roof azimuth -- from a single aerial orthophoto. Our approach extends Mask R-CNN with a dedicated attribute regression branch and introduces two key innovations: a conditional azimuth loss that suppresses supervision for flat roof segments where azimuth labels are inherently noisy, and a log-normalized height representation that addresses the heavily skewed distribution of building heights. We train and evaluate on a large-scale dataset of Dutch aerial images paired with automatically derived ground truth from 3DBAG, a nationwide LiDAR-based 3D building dataset. Using a DINOv3 ConvNeXt-Base backbone, our method achieves a mean absolute error of approximately 4 degrees for roof slope, 7 degrees for azimuth, and 1 meter for building height, with an instance segmentation AP$_{50}$ of 0.566. The predicted per-segment masks and attributes are sufficient to reconstruct simplified 3D building models (LoD2) from a single overhead image, requiring expensive 3D reference data only for training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。