Volume XLII-2
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 103-108, 2018
https://doi.org/10.5194/isprs-archives-XLII-2-103-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 103-108, 2018
https://doi.org/10.5194/isprs-archives-XLII-2-103-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 May 2018

30 May 2018

AUTOMATIC LARGE-SCALE 3D BUILDING SHAPE REFINEMENT USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORKS

K. Bittner1, P. d’Angelo1, M. Körner2, and P. Reinartz1 K. Bittner et al.
  • 1Remote Sensing Technology Institute, German Aerospace Center (DLR), Wessling, Germany
  • 2Technical University of Munich, Munich, Germany

Keywords: Conditional generative adversarial networks (cGANs), Digital Surface Model, 3D scene refinement, 3D building shape

Abstract. Three-dimensional building reconstruction from remote sensing imagery is one of the most difficult and important 3D modeling problems for complex urban environments. The main data sources provided the digital representation of the Earths surface and related natural, cultural, and man-made objects of the urban areas in remote sensing are the digital surface models (DSMs). The DSMs can be obtained either by light detection and ranging (LIDAR), SAR interferometry or from stereo images. Our approach relies on automatic global 3D building shape refinement from stereo DSMs using deep learning techniques. This refinement is necessary as the DSMs, which are extracted from image matching point clouds, suffer from occlusions, outliers, and noise. Though most previous works have shown promising results for building modeling, this topic remains an open research area. We present a new methodology which not only generates images with continuous values representing the elevation models but, at the same time, enhances the 3D object shapes, buildings in our case. Mainly, we train a conditional generative adversarial network (cGAN) to generate accurate LIDAR-like DSM height images from the noisy stereo DSM input. The obtained results demonstrate the strong potential of creating large areas remote sensing depth images where the buildings exhibit better-quality shapes and roof forms.