论文标题
SAT2PC：从2D卫星图像估算建筑屋顶的点云
sat2pc: Estimating Point Cloud of Building Roofs from 2D Satellite Images
论文作者
论文摘要
三维（3D）城市模型由于其在城市规划和虚拟现实等许多用例中的应用而引起了兴趣。但是，生成这些3D表示形式需要LiDAR数据，这些数据并不总是很容易获得。因此，自动3D模型生成算法的适用性仅限于几个位置。在本文中，我们提出了SAT2PC，这是一种深入学习的体系结构，可预测单个2D卫星图像的建筑屋顶的点云。我们的架构结合了倒角距离和EMD损失，从而获得了更好的2D至3D性能。我们广泛评估了我们的模型，并在建筑屋顶数据集上进行消融研究。我们的结果表明，SAT2PC能够胜过至少18.6％的现有基线。此外，我们表明，与其他基线相比，预测的点云捕获了更多的细节和几何特性。
Three-dimensional (3D) urban models have gained interest because of their applications in many use-cases such as urban planning and virtual reality. However, generating these 3D representations requires LiDAR data, which are not always readily available. Thus, the applicability of automated 3D model generation algorithms is limited to a few locations. In this paper, we propose sat2pc, a deep learning architecture that predicts the point cloud of a building roof from a single 2D satellite image. Our architecture combines Chamfer distance and EMD loss, resulting in better 2D to 3D performance. We extensively evaluate our model and perform ablation studies on a building roof dataset. Our results show that sat2pc was able to outperform existing baselines by at least 18.6%. Further, we show that the predicted point cloud captures more detail and geometric characteristics than other baselines.
