Boundary-Aware 3D Building Reconstruction From a Single Overhead Image
Boundary-Aware 3D Building Reconstruction From a Single Overhead Image
复制标题
DOI：
10.1109/cvpr42600.2020.00052
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Jisan Mahmud;True Price;Akash Bapat;Jan-Michael Frahm
中科院分区：
文献类型：
--
作者：
Jisan Mahmud;True Price;Akash Bapat;Jan-Michael Frahm
我们提出了一个从单个架空图像的快速3D构建建模的基于边界意识的多任务深度学习框架。与大多数依靠多个图像进行3D场景建模的技术不同，我们试图通过共同学习从建筑物边界，场景密集的高度图和场景语义的共同学习修改后的签名距离函数（SDF），从而从单个架空图像中对建筑物进行建模。为了共同训练这些任务，我们除了标记为构建大纲外，还利用像素的语义分割和标准化数字表面图（NDSM）作为监督。在测试时，场景中的建筑物仅使用输入台式图像自动在3D中建模。我们使用多功能网络体系结构来展示建筑建模性能的提高，该架构通过考虑为其他共同学习的任务学习的网络功能来改善构建轮廓检测。我们还介绍了一种新型的机制，用于使用学识渊博的修改后的SDF进行健壮的实例特定构建大纲。我们验证方法对多个大规模卫星和空中图像数据集的有效性，在该数据集中，我们可以在3D建筑重建任务中获得最先进的性能。
We propose a boundary-aware multi-task deep-learning-based framework for fast 3D building modeling from a single overhead image. Unlike most existing techniques which rely on multiple images for 3D scene modeling, we seek to model the buildings in the scene from a single overhead image by jointly learning a modified signed distance function (SDF) from the building boundaries, a dense heightmap of the scene, and scene semantics. To jointly train for these tasks, we leverage pixel-wise semantic segmentation and normalized digital surface maps (nDSM) as supervision, in addition to labeled building outlines. At test time, buildings in the scene are automatically modeled in 3D using only an input overhead image. We demonstrate an increase in building modeling performance using a multi-feature network architecture that improves building outline detection by considering network features learned for the other jointly learned tasks. We also introduce a novel mechanism for robustly refining instance-specific building outlines using the learned modified SDF. We verify the effectiveness of our method on multiple large-scale satellite and aerial imagery datasets, where we obtain state-of-the-art performance in the 3D building reconstruction task.