ARQGAN: an evaluation of Generative Adversarial Networks’ approaches for automatic virtual restoration of Greek temples Alberto Nogales 1 , Emilio Delgado 2 , Angel Melchor 1 , and Álvaro J. García-Tejedor 1 1 CEIEC Research Institute, Universidad Francisco de Vitoria, Ctra. M-515 Pozuelo-Maja- dahonda km. 1,800, 28223 Pozuelo de Alarcón (Madrid), Spain 2 Architecture School, Universidad Francisco de Vitoria, Ctra. M-515 Pozuelo-Majadahonda km. 1,800, 28223 Pozuelo de Alarcón (Madrid), Spain alberto.nogales@ceiec.es, e.delgado.prof@ufv.es, angelmelchorsanchez@gmail.com, a.gtejedor@ceiec.es Abstract. In the last years, Graphics Processing Units are evolving fast. This has had a big impact in several fields, such as Computer-Aided Design and particu- larly in 3D modeling, allowing the development of software for the creation of more detailed models. Nevertheless, building a 3D model is still a cumbersome and time-consuming task. Another field, that is evolving successfully due to this increase in computational capacity is Artificial Intelligence. These techniques are characterized among other things by the fact that they can automate tasks per- formed by humans. For example, reconstructing parts of images is being a hot topic recently. In this paper, a method based on Artificial Intelligence and in par- ticular Deep Learning techniques is proposed to achieve this task. The aim is to automatically restore Greek temples based on renders of its ruins obtained from 3D model representations. Results show that adding segmented images to the training dataset gives better results. Also, restoration of the general part of the temples is well performed but the detailed elements have room for improvement. Keywords: Neural networks; Deep Learning; Generative Adversarial Net- works; Cultural heritage; Virtual restoration; Greek temples. 1 Introduction European Commission surveys show that over 80% of the Europeans care about con- serving their cultural heritage 1 , with a particular interest in preserving historical sites as monuments or buildings. According to Berndt and Carlos (2000), the preservation of historical sites involves a range of different professionals, including art historians, ar- chaeologists, restorers, or architects. It also includes a wide range of activities such as digitalization, preservation, or restoration. The latter is defined as “returning the exist- ing fabric of a place to a known earlier state by removing accretions or by reassembling 1 https://what-europe-does-for-me.eu/en/portal/2/B35