VisionLab is one of the research laboratories in the Department of Computer Science at Sapienza University of Rome, Italy.
Think of VisionLab as a flight school for computers. We don’t just write code; we teach machines how to “see” the world just like humans do. If you’ve ever wondered how a self-driving car spots a pedestrian, how your phone recognizes your face to unlock, or how a robot navigates a room without bumping into furniture, that is Computer Vision. We collect data from cameras and sensors (the eyes) and develop the software (the brain) that enables them to understand, interpret, and react to what they observe, transforming pixels into intelligence.
Under the hood, our team is dedicated to the details of how this magic happens. We tackle a wide range of exciting challenges, including building eXtended Reality (XR) worlds, creating Generative AI models, and designing intelligent systems that analyze human behavior or detect diseases in medical scans. Crucially, we are also efficiency experts, figuring out how to shrink massive AI brains so they can run quickly on tiny devices, such as smartphones, without requiring a supercomputer to power them.
So, where do you fit in? If you are a student, VisionLab is your playground to experiment with cutting-edge tech, write a killer thesis, or launch a booming PhD career. For companies, we are your problem solvers. Whether you need to automate visual inspections, deploy AI on low-power hardware, or integrate advanced perception into your products, we have the expertise to make it happen. We are open for collaboration, research projects, and industrial partnerships: drop by and let’s build the future of machine perception together!