The study aims to assess the reliability of generative AI in predictive restoration by comparing the results of virtual restoration with those obtained through comparison with similar objects that are in a better state of preservation. The results presented reflect different stages in the training of AI models. The preliminary conclusions, based on the limited number of case studies examined, suggest that great caution is needed when using AI for predictive restoration, since the range of reference material available to AI is still too narrow. At present, graphic reconstruction based on direct examination of the objects and carried out using computer graphics tools appears to be more reliable.

Artificial Intelligence for Virtual Reconstruction of Polychromy in Painted Baroque Sculpture of Southern Italy

Raffaele CASCIARO
Primo
Writing – Review & Editing
;
Lucio Tommaso De Paolis
Validation
;
Letizia Cerrati
Writing – Original Draft Preparation
;
Mariachiara De Santis
Writing – Original Draft Preparation
;
Maura Lucia Sorrone
Membro del Collaboration Group
;
Ileana Riera Panaro
Membro del Collaboration Group
;
Giorgia De Giuseppe
Membro del Collaboration Group
2026-01-01

Abstract

The study aims to assess the reliability of generative AI in predictive restoration by comparing the results of virtual restoration with those obtained through comparison with similar objects that are in a better state of preservation. The results presented reflect different stages in the training of AI models. The preliminary conclusions, based on the limited number of case studies examined, suggest that great caution is needed when using AI for predictive restoration, since the range of reference material available to AI is still too narrow. At present, graphic reconstruction based on direct examination of the objects and carried out using computer graphics tools appears to be more reliable.
2026
978-3-032-33503-6
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11587/588606
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact