 This paper proposes a new method for surveying historical buildings and sites using crowdsourced images. It begins by collecting large data sets of images from the internet, which are filtered and analyzed using AI-based tools. Next, 3D reconstructions are created using structure from motion, SFM, and neural radiance fields, NERF. These reconstructions are then compared to high precision laser scans of large medieval churches to assess their accuracy. Additionally, the paper demonstrates the potential of this workflow in the field of building archaeology through detailed geometrical analyses of several iconic domes, including Hagia Sophia. Finally, it concludes that these crowdsourcing methods can enable remote and 4D surveys, opening up new opportunities for rapid, affordable, and borderless research on cultural heritage. This article was authored by L. Vandennebiel, M. Hackey, and M. Fister.