Recent breakthroughs in deep learning, including 3D Gaussian Splatting (3DGS) (Kerbl et al., 2024), have significantly advanced both the performance and visual quality of the reconstruction. Within our work, we focus on 3D mapping of complex, large-scale indoor environments such as construction sites and factory halls. This initiative is driven by a project within the Cluster of Excellence Integrative Computational Design and Construction for Architecture (IntCDC) at the University of Stuttgart, which aims to enable autonomous indoor construction for new or preexisting buildings (IntCDC, 2024a). Typical construction tasks, including material handling and element assembly, require highly accurate mapping approaches to enable precise localization of both building components and the construction robots. Image-based localization methods are particularly valuable due to the widespread availability and low cost of cameras, which are now standard equipment on most modern robots.

Simultaneous localization and mapping (SLAM), i.e., the reconstruction of the environment represented by a (3D) map and the concurrent pose estimation, has made astonishing progress. Meanwhile, large scale applications aiming at the data collection in complex environments like factory halls or construction sites are becoming feasible. However, in contrast to small scale scenarios with building interiors separated to single rooms, shop floors or construction areas require measures at larger distances in potentially texture less areas under difficult illumination. Pose estimation is further aggravated since no GNSS measures are available as it is usual for such indoor applications. In our work, we realize data collection in a large factory hall by a robot system equipped with four stereo cameras as well as a 3D laser scanner. We apply our state-of-the-art LiDAR and visual SLAM approaches and discuss the respective pros and cons of the different sensor types for trajectory estimation and dense map generation in such an environment. Additionally, dense and accurate depth maps are generated by 3D Gaussian splatting, which we plan to use in the context of our project aiming on the automatic construction and site monitoring.