Loggia dei Lanzi: AI Thermography Enhancement Comparisons through 3D Photogrammetry

2026-08-03

AI Summary

This study addresses the challenge of enhancing the visibility of subsurface architectural features in thermal imaging for cultural heritage documentation. It presents the first systematic comparison within a heritage-focused thermal imaging workflow among native resolution, hardware-based microscanning super-resolution (UltraMax), and AI-driven super-resolution techniques, evaluating their impact on feature detection and point matching in Structure-from-Motion–based 3D reconstruction. Experiments employed a FLIR T1020 HD thermal camera and integrated extended reality (XR) technologies to produce interactive 3D thermal archives. Results demonstrate that both AI and hardware super-resolution significantly improve model density and geometric accuracy, enabling city-scale XR applications. The project also publicly releases a comprehensive dataset to advance standardized adoption of thermal imaging in heritage digitization.

Abstract

The Loggia dei Lanzi in the Piazza della Signoria is one of Florence's most prominent structures visited by millions every year. Its construction history spans multiple centuries of modification. This paper presents the results of a thermal imaging campaign conducted in December 2025, using a FLIR T1020 HD camera, revealing hidden architectural features including walled-up openings and material transitions beneath the plaster surface. The favorable winter ambient conditions provided a feature-rich benchmark upon which to compare the results of enhancement algorithms and artificial intelligence models. We evaluate the application of AI-based image enhancement to thermal heritage documentation through a comparison of three tiers of image resolution in a photogrammetric Structure-from-Motion (SfM) pipeline: native resolution, FLIR's hardware-based pixel-shifted super-resolution (UltraMax), and state of the art AI-upscaled imagery models. We quantify the effect of each resolution tier on feature detection and tie-point generation, assessing whether the additional detail produced by super-resolution, whether hardware or AI-derived, translates into meaningfully denser and more accurate 3D thermal models. Our results contribute to the emerging intersection of artificial intelligence and heritage thermography by providing a direct comparison of hardware microscanning and AI super-resolution within a thermal photogrammetric workflow for cultural heritage. All datasets are made publicly available and accessible within an interactive 3D archival framework, and integrated into a custom citywide extended reality overlay application.

Problem

• thermal imaging
• super-resolution
• AI enhancement
• heritage documentation
• 3D photogrammetry

Innovation

• AI super-resolution
• thermal photogrammetry
• Structure-from-Motion
• heritage documentation
• extended reality