STARS Lab

In robotics and autonomous systems, visual-based localization is crucial for navigation and understanding the environment. Localization involves determining the position and orientation of a robot within a given space. This foundational capability enables advanced tasks like obstacle avoidance, path planning, and interaction in complex environments. Despite extensive research and development, visual localization remains a significant challenge, particularly under wide viewpoint and appearance changes.

Vincenzo is advancing robotics localization and mapping by integrating deep learning models and 3D scene modelling. His work focuses on addressing the persistent challenges of localization under varying viewpoints and appearances by developing adaptive and efficient representations of the environment. This research aims to enhance the robustness and scalability of robotic systems, enabling them to operate effectively in dynamic and diverse real-world settings.

@misc{polizzi2024arXiv,
    title={FaVoR: Features via Voxel Rendering for Camera Relocalization},
    author={Vincenzo Polizzi and Marco Cannici and Davide Scaramuzza and Jonathan Kelly},
    year={2024},
    eprint={2409.07571},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2409.07571},
}