Synthesis and Completion of Facades from Satellite Imagery

Synthesis and Completion of Facades from Satellite Imagery
复制标题

卫星图像的外立面合成和完成

DOI:
10.1007/978-3-030-58536-5_34
复制
发表时间:
2020
期刊:
European Conference on Computer Vision
影响因子:
--
通讯作者:
Aliaga, D.
Aliaga, D.
中科院分区:
--
文献类型:
--
作者:
Zhang, X.;May, C.;Aliaga, D.

文献摘要

参考文献

被引文献

相似文献

基于卫星的自动重建能够实现大规模、广泛的城市地区的创建。然而,卫星图像通常有噪声且不完整,不适合重建详细的建筑立面。我们提出了一种基于机器学习的逆向程序建模方法,可以根据卫星图像自动创建合成立面。我们的主要观察结果是,建筑立面呈现出规则的网格状结构。因此,我们可以通过合成底层立面布局来克服从卫星图像获得的低分辨率、噪声和部分建筑数据。我们的方法从基于卫星的建筑物图像片段推断出规则的立面细节,并将其应用于建筑物的遮挡或采样不足的部分,从而产生合理、清晰的立面。使用六个城市的市区,我们将我们的方法与几种最先进的图像完成/填充方法进行比较,我们的方法始终能够创建更好的立面图像。
Automatic satellite-based reconstruction enables large and widespread creation of urban areas. However, satellite imagery is often noisy and incomplete, and is not suitable for reconstructing detailed building facades. We present a machine learning-based inverse procedural modeling method to automatically create synthetic facades from satellite imagery. Our key observation is that building facades exhibit regular, grid-like structures. Hence, we can overcome the low-resolution, noisy, and partial building data obtained from satellite imagery by synthesizing the underlying facade layout. Our method infers regular facade details from satellite-based image-fragments of a building, and applies them to occluded or under-sampled parts of the building, resulting in plausible, crisp facades. Using urban areas from six cities, we compare our approach to several state-of-the-art image completion/in-filling methods and our approach consistently creates better facade images.
从极高分辨率多视图卫星图像中自动进行 3D 恢复
DOI: --
发表时间: 2019
期刊: arXiv.org
影响因子: --
作者:
R. Qin
通讯作者: R. Qin
卫星图像 3D 几何的最小求解器
DOI: --
发表时间: 2015
期刊: IEEE International Conference on Computer Vision
影响因子: --
作者:
Enliang Zheng;Ke Wang;Enrique Dunn;Jan
通讯作者: Jan