SemDpray: Virtual reality as-is semantic information labeling tool for 3D spatial data

Capturing the as-is status of buildings in the form of 3D spatial data (e.g., point cloud or mesh) with the use of 3D sensing technologies is becoming predominant in the Architecture, Engineering, and Construction (AEC) industry. Although the act of acquiring this data has been progressively becoming more accurate and efficient with the availability of off-the-shelf solutions in the market, the act of extracting from it as-is information has not seen similar advancements. State-of-the-art practice requires experts to manually interact with the spatial data in a labo-rious and time-consuming process. We propose Semantic Spray ( Semspray ), a Virtual Reality (VR) application that provides users with intuitive and handy tools to produce semantic information on as-is 3D spatial data (mesh) of buildings. The goal is to perform this task accurately and more efficiently by allowing users to experience, interact with, and immerse themselves in the data at different scales. Semspray is a combination of two labeling modes: user-dynamic and user-static . In the user-dynamic mode, the user is fully immersed in the 3D mesh and has the ability to walk and teleport themselves within the model; in the user-static , the user can comfortably sit on a chair and handle a small-scale version of the 3D mesh to perform the labeling, in a similar manner to hand-held painting. We evaluated SemSpray ’s performance with a user study of ten participants and found that the combination of the different modes is able to keep the user entertained and to limit the side-effect of VR on the sensory organs, including nausea, headache, and dizziness.