HoloLabel: Augmented reality user-in-the-loop online annotation tool for as-is building information

Dhruv Agrawal, Janik Lobsiger, Jessica Yi Bo, Véronique Kaufmann, Iro Armeni
DOI: 10.35490/EC3.2022.174
Abstract: 3D sensing devices simplify the task of capturing and reconstructing an environment as a spatial 3D mesh. However, the task of converting this purely geometric information to a semantically meaningful as-is building model is non-trivial. State-of-the-art practice follows a first step of acquiring the spatial 3D mesh on site and subsequently resorts in manual semantic labeling in the office, where experts have to work for many hours using non-intuitive and error-prone tools. We develop HoloLabel, an Augmented Reality application that allows users to directly and on-site annotate a scene in 3D with rich semantic information while simultaneously capturing its spatial 3D mesh.
Keywords: as-is building information, augmented reality, semantic segmentation

Presentation video

Successfully submitted

Your submission has been received. We will review your details and contact you soon.