PhD Candidate
Pubblicato il 20-08-2026 - Altro in Roma
Organisation/Company Fondazione Bruno Kessler Research Field Other Researcher Profile Other Profession Positions PhD Positions Application Deadline 28 Aug 2026 - 23:59 (Europe/Rome) Country Italy Type of Contract Temporary Job Status Full-time Offer Starting Date 1 Nov 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No
Offer Description This PhD project focuses on the development of advanced methods for high-quality 3D reconstruction and surface modelling to support accurate, reliable, and scalable representations of real-world environments, objects, and systems. The research will investigate approaches capable of integrating heterogeneous input sources, including images, video streams, LiDAR, RGB-D cameras, and other sensing modalities, under different computational and operational constraints. The project will address key challenges in generating 3D representations suitable for high-precision measurement,
digital twin creation,
and the development of world models for intelligent systems. This includes studying reconstruction pipelines that can adapt to different levels of accuracy, latency, and computational resources, ranging from real-time perception scenarios to offline high-fidelity reconstruction. A central aspect of the research will be the exploration of trustworthy and explainable 3D reconstruction methods, aiming to improve the transparency, robustness, and reliability of reconstructed models. Particular attention will be given to how uncertainty, reconstruction quality, and measurement
confidence can be estimated, communicated, and exploited in downstream applications.
The expected outcome is the development of novel algorithms and frameworks for robust, accurate, and explainable 3D modelling, with potential applications in robotics, industrial inspection, autonomous systems, metrology, simulation, digital twins, and spatial intelligenc