Augmented Reality (AR) has been extensively investigated as a tool for remote assistance across various application domains, such as industrial maintenance and home support. In this context, a user operating within an AR-enabled system may solicit guidance from remote collaborators who possess visual access to the physical environment. To facilitate effective collaboration, it is imperative that remote users maintain a comprehensive understanding of the physical workspace, a requirement referred to as workspace awareness. Workspace awareness enables the remote collaborators to understand and assess the environment in which the co-located user is located. A wide range of works have explored to present AR workspaces to remote users [Assaf et al.]. Most of the works focuses on static 3D reconstructions [Kumaravel et al.], virtual proxies [Oda et al.], light fields [Mohr et al.] or real-time video feeds [Fages et al.]. All methods present several trade-offs, based on the size of the reconstructed workspace, the freedom that remote users have to navigate through the reconstructed workspace, the fidelity of the reconstructed workspace or the required preparation and instrumentation. While video provides high fidelity with minimal instrumentation, the navigation capability for remote users is limited and only provide a partial view of the workspace. However, due to the difficulty to ensure free exploration for remote collaborators, workspace awareness still remains an open problem, and it is typically supported either by virtual replicas/reconstructions or video feeds [4]. The appearance of 3D Gaussian Splatting (3DGS) methods [Kerbl et al.] [Meuleman et al.], real-time and high-fidelity reconstruction of physical workspaces is nowadays possible, there is still little research on how the online reconstruction process can be executed in real time without any instrumentation and still ensure a smooth collaboration among different actors. In this context, the first objective of the PhD is to evaluate collaborative incremental reconstruction methods to efficiently support workspace awareness even in the context of partial or uncertain reconstructions, and propose interaction methods to incrementally refine the dynamic reconstruction. Furthermore, workspace awareness is not solely limited to the visual modality, a second objective of the PhD is exploring methods to enrich the reconstruction inferring other sensory modalities, notably haptic information, using the capability of novel view synthesis and vision-based scene understanding methods [Park et al.]. In addition to the technical contributions, specific focus will be devoted the perceptual assessment of the reconstructed models to ensure that 3DGS methods do not introduce perceptual biases.
