Can Artificial Intelligence Reconstruct Ancient Mosaics?

A large number of ancient mosaics are no longer available to us because they have been destroyed by erosion, earthquakes, looting, or even used as materials in newer construction. To make things worse, among the small fraction of mosaics that have been recovered, many are damaged or incomplete. Therefore, it is of interest to explore how the mosaics may have appeared originally by using virtual reconstruction. This has traditionally been done manually and more recently using computer graphics programs but always by humans. In the last few years, artificial intelligence (AI) has made impressive progress in the generation of images from text descriptions and reference images. State-of-the-art AI tools such as DALL-E2 can generate high-quality images from text prompts and can take a reference image to guide the process. In August 2022, DALL-E2 launched a new feature called outpainting that takes as input an incomplete image and a text prompt and then generates a complete image filling in the missing parts. In this paper, we explore whether this innovative technology can be used to perform virtual reconstruction of mosaics with missing parts. Hence, a set of ancient mosaics have been selected and DALL-E2 has been used to create virtual reconstructions; the results are promising, showing that AI is able to interpret the key features of the mosaics and is able to produce virtual reconstructions that capture the essence of the scene. However, in some cases AI does not reproduce some details or geometric forms or introduces elements that are not consistent with the rest of the mosaic. This suggests that when AI image generation technology matures in the next few years, it could be a valuable tool to create virtual reconstructions of mosaics in the future. [ABSTRACT FROM AUTHOR]