Building Information Modelling (BIM) is a new process that is spreading in the Architecture, Engineering and Construction field. It allows the creation of virtual building models, which can be linked to numerical data, texts, images, and other types of information. Building components, such as walls, floors, etc. are modelled as “smart objects”, i.e. they are defined by numerical parameters, such as dimensions, and are embedded with other kinds of information, such as building materials and properties. Stored data are accessible and modifiable by all different professionals involved in the same project. The BIM process has been developed for new buildings, and it allows to plan and manage the whole building life-cycle. BIM for built heritage has started to be researched recently, and its use is still not widespread. Indeed, built heritage is characterised by complex morphology and non-homogeneous features, which clash with BIM’s standardised procedures. Moreover, to date, BIM does not allow fully automated procedures to model heritage buildings. This review focuses on the survey and digitisation phases, which can be seen as the initial phases of application of BIM in conservation projects. It also briefly covers the modelling stage. Here we present the main methodologies developed for BIM for built heritage. Issues about digitisation are also highlighted, principally in connection with the unavailability of automated processes. During the last 10 years, research has led to promising results; for example, videogame interfaces have been used to simulate virtual 3D tours that display in a single interface the 3D model and the database containing metadata, and new software plug-ins have been developed, to easily create “smart objects”. Nevertheless, further research is needed to establish how BIM can support the practice of building conservation. There is a gap in BIM’s information holding capacities, namely the storage of cultural and historical documentation, as well as monitored and simulated data relevant for preventive conservation. Future work should focus on the development of new tools that will be able to store and share all the relevant metadata.

The need for better 3D documentation of the built environment has come to the fore in recent years, led primarily by city modelling at the large scale and Building Information Modelling (BIM) at the smaller scale. Automation is seen as desirable as it removes the time-consuming and therefore costly amount of human intervention in the process of model generation. BIM is the focus of this paper as not only is there a commercial need, as will be shown by the number of commercial solutions, but also wide research interest due to the aspiration of automated 3D models from both Geomatics and Computer Science communities. The aim is to go beyond the current labour-intensive tracing of the point cloud to an automated process that produces geometry that is both open and more verifiable. This work investigates what can be achieved today with automation through both literature review and by proposing a novel point cloud processing process. We present an automated workflow for the generation of BIM data from 3D point clouds. We also present quality indicators for reconstructed geometry elements and a framework in which to assess the quality of the reconstructed geometry against a reference.

Over the past decade deep learning has driven progress in 2D image understanding. Despite these advancements, techniques for automatic 3D sensed data understanding, such as point clouds, is comparatively immature. However, with a range of important applications from indoor robotics navigation to national scale remote sensing there is a high demand for algorithms that can learn to automatically understand and classify 3D sensed data. In this paper we review the current state-of-the-art deep learning architectures for processing unstructured Euclidean data. We begin by addressing the background concepts and traditional methodologies. We review the current main approaches, including RGB-D, multi-view, volumetric and fully end-to-end architecture designs. Datasets for each category are documented and explained. Finally, we give a detailed discussion about the future of deep learning for 3D sensed data, using literature to justify the areas where future research would be most valuable.