Bridging the past and present: AI-driven 3D restoration of degraded artefacts for museum digital display

Artificial intelligence can lend a helpful digital "hand" in the restoration process of deteriorated cultural heritage items as well as towards an increased visitor interest in the museum exhibits. To this purpose, the present paper proposes a deep learning approach to repair the missing content and to recreate a visual counterpart of a degraded artefact by a 3D rendering of the semantic inpainted version. The new approach is constructed by means of some of the most recent and successful deep learning models for image inpainting and 3D reconstruction, namely stable diffusion and neural radiance fields. The method is tested in the scenario of ceramic artefacts, where the end visual result has a bigger impact. The ability of the novel technique to creatively reproduce a realistic and plausible 3D surrogate of broken archaeological objects shows the potential that AI has in supporting specialists with preserving the cultural heritage and bringing the museums into the public spotlight. (c) 2024 Consiglio Nazionale delle Ricerche (CNR). Published by Elsevier Masson SAS. All rights are reserved, including those for text and data mining, AI training, and similar technologies.