Cultural heritage faces accelerating threats from armed conflict and climate-induced disasters, generating emergency scenarios in which the window for documentation may be measured in hours. Traditional high-fidelity workflows such as Terrestrial Laser Scanning and survey-grade Structure-from-Motion campaign can be operationally incompatible with these constraints due to costly hardware and specialist-team requirements. Emergency image acquisition can be undertaken with consumer-grade equipment, while the same photographic dataset can subsequently support both an SfM-MVS mesh for metric and geometric analysis and a 3D Gaussian Splatting (3DGS) representation for view-dependent visual interpretation. This paper evaluates an accessible, entirely graphical workflow for producing these complementary outputs, with particular attention paid to the 3DGS stage and without requiring programming or command-line expertise. We develop a theoretical case drawing on Brandinian restoration theory and the international conservation framework, introducing the concept of informational amnesia, the irreversible loss of a site’s documentary record, as a distinct and undertheorized category of heritage failure. We further argue that the democratization of 3DGS documentation cannot be measured by licensing cost alone: a tool distributed as open-source code but requiring command-line expertise presents an effective accessibility barrier functionally equivalent to a commercial paywall. True accessibility requires installable, graphical software operable by non-specialist practitioners in the field. We present a proof-of-concept application of this accessible pipeline, namely DJI Mini 5 Pro, RealityScan for photogrammetric reconstruction, and Lichtfeld Studio for 3DGS generation, to the Fontana d’Ercole at the Reggia di Venaria Reale (UNESCO World Heritage, Turin, Italy). Visual results show photorealistic, navigable 3DGS surrogates of architecturally complex heritage assets achievable by non-specialist operators within hours of acquisition and establish the empirical foundation for future quantitative evaluation.
Alessio Martino, F. Chiabrando· The Heritage· 0 citations
Abstract. This paper presents a comparative analysis of traditional photogrammetric methods and 3D Gaussian Splatting (3DGS) technology in the digitisation of Cultural Heritage (CH). Two representative datasets, differing in scale and image acquisition conditions, were selected to systematically evaluate the performance of both methods in terms of visual quality, geometric accuracy, computational efficiency and stability. The results indicate that 3DGS significantly outperforms traditional photogrammetry methods in terms of rendering quality and real-time visualisation capabilities, generating more realistic and immersive visual effects. However, its geometric accuracy is generally slightly lower than that of traditional methods, a difference that is particularly pronounced in small-scale datasets or under low-resolution input conditions. Among the various implementation methods, Postshot and LichtFeld Studio demonstrated higher stability and robustness, whilst the original GraphDeco method exhibited greater sensitivity to data scale and parameter settings. Photogrammetry offers reliability in high-precision geometric reconstruction, whilst 3DGS demonstrates significant potential for complementing this with a high-fidelity visual experience. The research findings try to provide practical guidance for selecting 3D reconstruction methods across different cultural heritage application scenarios.
Xinchen Li, Alessio Martino, F. Chiabrando et al.· The International Archives o...· 0 citations
Abstract. Monocular depth estimation (MDE) has reached notable maturity in computer vision, yet its application to UAV-based architectural heritage documentation remains underexplored. This study assesses whether the depth foundation model Depth Anything V2 can be transferred from terrestrial to aerial imagery. The analysis relies on MDE4BH, a benchmark of over 3,000 UAV images covering ten heterogeneous heritage scenarios (urban areas, façades, towers, villas, domes, and archaeological sites). Masked photogrammetric depth maps serve as metric reference for calibration, validation, and supervised retraining. Two baseline configurations are evaluated: a relative model with scene-specific linear rescaling and the direct application of the metric model. The rescaled relative model shows acceptable performance in several subsets, whereas the metric model exhibits systematic bias, weak consistency, and scale collapse due to domain shift between terrestrial training data and aerial acquisition geometry. To address these limitations, a two-step fine-tuning strategy is introduced, focusing on the decoder and regression head. The first stage uses mainly oblique UAV images; the second integrates oblique and nadir views to improve viewpoint generalization. The adapted model significantly reduces bias and enhances metric stability across the benchmark. However, residual errors remain spatially structured, with clustering and recurrent artefacts near object boundaries, multi-level roofs, and radiometrically heterogeneous surfaces. Although accuracy is still insufficient for demanding metric applications, the results support the use of MDE as a complementary source for thematic interpretation, scene understanding, robotics, navigation, and related tasks where strict geometric precision is not required.
F. Chiabrando, Francesca Gallitto, A. Lingua et al.· The International Archives o...· 0 citations
The first results of the AI-based processing pipeline developed within the HERITALISE project are presented, applied to three multiscale case studies at the Reggia di Venaria Reale, demonstrating strong photorealistic rendering capabilities, particularly for complex material properties and geometrically challenging interiors, whilst highlighting current limitations for metric surveying applications.
F. Chiabrando, A. Lingua, Alessio Martino et al.· The International Archives o...· 0 citations