The paper presents a multi-platform application based on point cloud data to support the conservation and dissemination of a medieval stone village. The workflow integrates 3D survey techniques—laser scanning, mobile mapping, and photogrammetry—to generate temporal datasets documenting different stages of restoration. Instead of relying on mesh-based reconstruction, the study proposes the direct use of point clouds as rendering primitives within interactive environments developed in Unity. The application is designed for multiple platforms (mobile AR, PC/web, and VR), each tailored to specific user needs and hardware constraints, enabling both professional access to detailed documentation and public engagement through immersive storytelling. The system incorporates interactive features such as time-travel navigation, point cloud visualization control, and narrative content layers, positioning the project as a hybrid tool for conservation support, education, and virtual heritage exploration.
VR and Holographic Information System for the Conservation Project
This paper presents an advanced digital workflow that integrates virtual reality and holographic visualization systems to support conservation planning and heritage management. The research addresses a common limitation in heritage digitization: although laser scanning and photogrammetry produce accurate 3D datasets, these models are often reduced to traditional 2D drawings, losing spatial richness and informational potential. To overcome this issue, the authors propose the direct use of point clouds enriched with semantic data, linked to a PostgreSQL database and visualized through immersive and collaborative environments. A VR application developed in Unity enables first-person exploration of the surveyed site, hotspot creation, and on-site compilation of conservation factsheets. In parallel, a Euclideon Hologram Table allows multiple users to inspect the same three-dimensional dataset simultaneously, facilitating collective analysis and project discussion. The methodology demonstrates how point clouds can become operative information systems rather than passive survey outputs. The study highlights the educational and professional value of combining accurate survey data, shared interfaces, and interactive visualization tools for heritage preservation, diagnosis, and reuse strategies.
Machine Learning for Cultural Heritage Classification
Cultural Heritage (CH) assets may be defined as integrated spatial systems composed of inter-connected shapes. The classification and organization of geometries within a hierarchical system are functional to their correct interpretation, which is often performed using 3D point clouds. The recurring shapes recognition becomes a crucial activity, nowadays accelerated by Machine Learning (ML) procedures able to associate semantic meaning to geometric data. An interdisciplinary research team [1] has developed a ML supervised approach, tested on the Milan Cathedral and Pomposa Abbey datasets, which presents an innovative multi–level and multi–resolution classification (MLMR) process. The methodology improves the learning activity and optimizes the 3D classification by a hierarchical concept.
A Hierarchical Machine Learning Approach for Multi-Level and Multi-Resolution 3D Point Cloud Classification
The recent years saw an extensive use of 3D point cloud data for heritage documentation, valorisation and visualisation. Although rich in metric quality, these 3D data lack structured information such as semantics and hierarchy between parts. In this context, the introduction of point cloud classification methods can play an essential role for better data usage, model definition, analysis and conservation. The paper aims to extend a machine learning (ML) classification method with a multi-level and multi-resolution (MLMR) approach. The proposed MLMR approach improves the learning process and optimises 3D classification results through a hierarchical concept. The MLMR procedure is tested and evaluated on two large-scale and complex datasets: the Pomposa Abbey (Italy) and the Milan Cathedral (Italy). Classification results show the reliability and replicability of the developed method, allowing the identification of the necessary architectural classes at each geometric resolution.