Digital twins and immersive mixed reality have been improving digital transformation within the industrial context. In computer vision, photogrammetry-based techniques for 3D environment reconstruction make it possible to create virtual models of real scenery based on a set of digital images. This paper addresses the problem of building virtual layouts through the 3D mapping of the real environment and its corresponding digital twin, with a focus on human interaction and training. In the context of human-in-the-loop and Industry 5.0, the research goal is to define a method for preparing humans to be trained using synthetic information, enabling them to perform the real operations required in some productive processes. Through photogrammetry using images, layouts and objects can be recreated, but it is essential to evaluate the accuracy and richness of details to reconstruct a realistic process. Thus, we studied the main technological requirements to perform an automated method for shop-floor layout digitalization and digital twin creation, allowing humans to interact and simulate operations as in a real industrial scenario. The research conducts this investigation using a manufacturing automation laboratory and addresses experimental digitalization task planning.