This study integrates artificial intelligence and computational design tools to extract in- formation from architectural heritage. Photogrammetry-based point cloud models of brick walls from the Anatolian Seljuk period are analysed in terms of the interrelated units of construction, simultaneously considering both the inherent symmetries and irregularities. The real-world data is used as input for acquiring the stochastic parameters of spatial relations and a set of parametric shape rules to recreate designs of existing and hypothetical brick walls within the style. The motiva- tion is to be able to generate large data sets for machine learning of the style and to devise proce- dures for robotic production of such designs with repetitive units.

Existing digital reconstruction methods recover geometry alone and were not designed for bridge infrastructure, where form and structural behavior are inseparable. We present BriRet, an ML-based retrieval approach that aligns the latent representations of graphs and renders of structures to retrieve a 3D bridge model from a 2D image, providing both geometric and structural properties. We use Combinatorial Equilibrium Modeling (CEM), a computational form-finding method, to represent 3D structural models as structural graphs encapsulating both geometry and internal forces. Trained with a contrastive objective on a synthetic bridge dataset, BriRet retrieves structurally valid graphs from a single rendered view, reaching over 90\% top-1 graph similarity and returning models in under 70 ms. This work establishes a foundation for reconstructing bridge infrastructure in static equilibrium, supporting conceptual design by enabling designers to rapidly retrieve and iterate on structurally valid models from a single image.