Performance benchmarking of scan-to-HBIM workflows for cultural heritage (2012–2025)

Abstract

This paper conducts a comprehensive systematic review of Scan-to-HBIM workflows from 2012 to 2025, examining methodological structures, algorithmic support, and application maturity within digital workflows for cultural heritage documentation and management. The review synthesises global literature to classify contributions across technical domains: geometric acquisition, condition assessment, AI-assisted modelling, performance benchmarking, semantic enrichment, and immersive VR/AR applications, alongside the emerging cultural value dimension. The findings indicate a progressive shift toward hybrid human–algorithm workflows, combining deep learning, rule-based modelling, and semantic knowledge structures, rather than fully automated pipelines. Accuracy benchmarking highlights persistent inconsistencies in reporting frameworks across RMSE, IoU, and level-of-detail metrics, underscoring the need for greater methodological transparency. The paper concludes by identifying standardisation, interoperable data governance, and selective, scalable semantic AI integration as critical priorities for advancing reliable and sustainable Scan-to-HBIM practice in cultural heritage contexts.