Publications / 2020 Proceedings of the 37th ISARC, Kitakyushu, Japan

Synthetic Data Generation for Indoor Scene Understanding Using BIM

Yeji Hong, Somin Park and Hyoungkwan Kim
Pages 334-338 (2020 Proceedings of the 37th ISARC, Kitakyushu, Japan, ISBN 978-952-94-3634-7, ISSN 2413-5844)

Visual facility inspections performed manually are tasks that can be automated. Segmentation of facility image data is one of the automated methods of identifying problems in facilities. However, the machine learning methodology that is mainly used to train the segmentation model requires a large amount of training dataset. Preparing training dataset accompanies laborious manual labeling. To address this issue, we present a new method for generating synthetic data that do not require manual labeling. The method is to create photograph-style images from the BIM images; a generative adversarial network called CycleGAN is used to enable style transfer between the two different domains.

Keywords: BIM; Cycle-Consistent Adversarial Networks (CycleGAN); Facility Management; Scene Understanding; Synthetic Data