Computer vision researchers working at MBZUAI focus on teaching computers to interpret and understand visual information, enabling tasks like image recognition, object detection, and video analysis.
MBZUAI researchers develop visual and vision-language AI models, focusing on robotic vision, generative media, multi-sensor fusion, and trustworthy AI.
Our students, supervised by our world-class faculty, get unique hands-on experience by developing and evaluating real-world applications in augmented and virtual reality, autonomous cars, service robots, biometrics and forensics, remote sensing, and smart cities.
Our University offers Ph.D. and M.Sc. degrees in computer vision with advanced courses and outcomes.
A new framework from MBZUAI researchers helps AI systems remain effective when data is scarce and inputs.....
Read MoreMBZUAI researchers have developed a new approach to video understanding that reduces computational costs while maintaining accuracy.
Read MoreA new system developed by MBZUAI embeds unique, key-driven watermarks into AI-generated videos, making synthetic content more.....
Read More