LSTM Architectures for Facade Structure Completion

Simon Hensel, Steffen Goebbels, Martin Kada

Abstract

3D city models are often generated from oblique aerial images and photogrammetric point clouds. In contrast to roof surfaces, facades can not directly be reconstructed in a similar high level of quality from this data. Distortions of perspective might appear in images, due to the camera angle. Occlusions and shadowing occur as well. Objects, such as windows and doors, will have to be detected on such data if facades are to be reconstructed. Although one can use inpainting techniques to cover occluded areas, detection results are often incomplete and noisy. Formal grammars can then be used to align and add objects. However, it is difficult to find suitable rules for all types of buildings. We propose a post-processing approach based on neural networks to improve facade layouts. To this end, we applied existing Recurrent Neural Network architectures like Multi-Dimensional Long Short-term Memory Network and Quasi Recurrent Neural Network in a new context. We also propose a novel architecture, the Rotated Multi-Dimensional Long Short Term Memory. In order to deal with two-dimensional neighborhoods this architecture combines four two-dimensional Multi-Dimensional Long Short-term Memory Networks on rotated images. We could improve the quality of detection results on the Graz50 data set.

Download


Paper Citation


in Harvard Style

Hensel S., Goebbels S. and Kada M. (2021). LSTM Architectures for Facade Structure Completion.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, ISBN 978-989-758-488-6, pages 15-24. DOI: 10.5220/0010194400150024


in Bibtex Style

@conference{grapp21,
author={Simon Hensel and Steffen Goebbels and Martin Kada},
title={LSTM Architectures for Facade Structure Completion},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,},
year={2021},
pages={15-24},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010194400150024},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,
TI - LSTM Architectures for Facade Structure Completion
SN - 978-989-758-488-6
AU - Hensel S.
AU - Goebbels S.
AU - Kada M.
PY - 2021
SP - 15
EP - 24
DO - 10.5220/0010194400150024