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 PaolisValidation
;Letizia CerratiWriting – Original Draft Preparation
;Mariachiara De SantisWriting – Original Draft Preparation
;Maura Lucia SorroneMembro del Collaboration Group
;Ileana Riera PanaroMembro del Collaboration Group
;Giorgia De GiuseppeMembro 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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


