Building pop-up habitats in extreme weather conditions such as deserts requires preliminary contextual, i.e., site studies. Since the site’s condition is constantly changing due to sand relocation induced by wind, a rapid mapping solution is proposed. This is implemented by generating a 3D mesh model of the site with the help of a visual workflow and advanced computational design methods to implement in-situ 3D printing of habitats. This paper presents an integrated approach utilizing Computer Vision (CV), Deep Learning (DL), and generative design tools like Grasshopper. By harnessing the potential of Convolutional Neural Networks (CNNs), a robust framework is developed to recognize complex desert terrain features, independent of solar orientation and camera positioning. The methodology employs a state-of-the-art CNN customized for detecting features in desert settings. This is further enhanced by using Grasshopper to systematically generate a diverse dataset that enriches the model’s learning process. The resulting model efficiently extracts precise 3D meshes from 2D images, optimizing site mapping and integrating habitat printing workflows. This automated approach offers an effective solution for habitat construction in challenging environments, showcasing real-time processing.