Enhancing detail of 3D terrain models using GAN

Vladimir Gorbatsevich; Mikhail Melnichenko; Oleg Vygolov

doi:10.1117/12.2525177

21 June 2019 Enhancing detail of 3D terrain models using GAN

Vladimir Gorbatsevich, Mikhail Melnichenko, Oleg Vygolov

Proceedings Volume 11057, Modeling Aspects in Optical Metrology VII; 110571D (2019) https://doi.org/10.1117/12.2525177
Event: SPIE Optical Metrology, 2019, Munich, Germany

Abstract

The paper addresses the problem of low quality 3D terrain models enhancement. We propose the approach based on convolutional neural networks (CNN), namely, on Pix2Pix method that uses generative adversarial networks for imageto-image translation. We use heightmap 3D terrain models representation to use classical CNNs. The network was trained on a synthetic dataset that included 150000 images and heightmaps of different landscapes. Our model showed the relative mean absolute difference equal to 0.459% on synthetic testing dataset. In addition, we demonstrate landscapes generation on the real data from Google Maps using our model.

Citation Download Citation

Vladimir Gorbatsevich, Mikhail Melnichenko, and Oleg Vygolov "Enhancing detail of 3D terrain models using GAN", Proc. SPIE 11057, Modeling Aspects in Optical Metrology VII, 110571D (21 June 2019); https://doi.org/10.1117/12.2525177

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available