Raiders of the Lost Art

TL;DR

This paper introduces a novel neural style transfer method to reconstruct lost artwork from x-radiographs, enabling the recovery of hidden or damaged art pieces and exploring the broader implications of AI art.

Contribution

The paper presents a new application of neural style transfer for reconstructing lost artworks from radiographic images, combining technical innovation with cultural analysis.

Findings

Successful reconstruction of hidden artwork using style transfer

Enhanced understanding of art restoration through AI techniques

Discussion on ethical and cultural impacts of AI in art

Abstract

Neural style transfer, first proposed by Gatys et al. (2015), can be used to create novel artistic work through rendering a content image in the form of a style image. We present a novel method of reconstructing lost artwork, by applying neural style transfer to x-radiographs of artwork with secondary interior artwork beneath a primary exterior, so as to reconstruct lost artwork. Finally we reflect on AI art exhibitions and discuss the social, cultural, ethical, and philosophical impact of these technical innovations.