The paper investigates the evolution of AI-assisted architectural representation from early unpredictable text-to-image generation systems toward more controlled and precise workflows based on Stable Diffusion, ControlNet, and LookX AI. The research analyzes the role of latent spaces, diffusion models, GANs, convolutional neural networks, and AI rendering systems in architectural visualization, emphasizing the transition from exploratory AI image production to controllable design-oriented generation. Through experimental workflows combining Rhinoceros 3D models, ControlNet preprocessors, segmentation maps, depth maps, edge detection, and prompt engineering, the study evaluates how AI systems can support architectural rendering, stylistic control, spatial coherence, and atmosphere generation. The paper compares open-source and cloud-based AI platforms, discussing the balance between creativity, predictability, customization, and architectural precision in contemporary AI-assisted design workflows.
Neural Networks as an Alternative to Photogrammetry. Using Instant NeRF and Volumetric Rendering
This paper investigates Neural Radiance Fields (NeRF) as an emerging alternative to traditional photogrammetry for the digital acquisition of heritage objects and environments. The study reviews recent developments in machine learning and computer vision, focusing on NVIDIA Instant NeRF, volumetric rendering, and related platforms such as Luma AI and Nerfstudio. Unlike conventional photogrammetry, NeRF systems reconstruct scenes through neural networks that infer missing views and generate volumetric representations with realistic lighting, reflections, and textures. The authors test these methods on a sculptural case study, evaluating speed, geometric quality, mesh extraction, texture generation, and interoperability with external software such as Blender and Unreal Engine. Results show that NeRF workflows can reduce acquisition and processing times while performing particularly well on reflective materials and complex lighting conditions, areas where photogrammetry often struggles. Although current outputs still present limitations in mesh closure, topology control, and metric reliability, the research suggests that neural rendering may soon become a powerful tool for digital twins, immersive heritage visualization, and future survey practices.
Evolutionary Time Lines, Hypothesis of an AI+AR–Based Virtual Museum
The contribution related to the processes of knowledge and enhancement of cultural heritage, based on the potential offered by Artificial Intelligence and Augmented Reality, proposes an analysis of the sit-uation of L’Aquila’s buildings ten years after the 2009 earthquake. The research, conducted on the basis of integrated surveys carried out before and after the earthquake, focuses on the application of AR/ VR devices through the implementation of AI. The aim is to propose a solution able to promote the use of the historical buildings of L’Aquila, activating at the same time the dynamics of cultural regeneration in the area, through the use of an App that uses AR+AI systems; a tour that can show with immediacy the urban architectural evolution, solving in part the intrinsic difficulties posed by the current situation of precarious visibility and accessibility of some noble buildings, subject to restoration, with the aim of highlighting the evolution of transformations, stylistic and structural changes produced by the different and stratified post–earthquake reconstructions.