Our research group focuses on the development of advanced computational methods at the intersection of artificial intelligence, image processing, and immersive technologies, with a strong emphasis on real-world applicability and societal impact.
We combine deep learning, medical and visual data analysis, and generative modeling to create robust, interpretable, and scalable intelligent systems. A key aspect of our work is the development of advanced computational methods for medical image analysis using CT and MRI. Our focus is on automated segmentation, quantitative analysis, and interpretation of various anatomical structures to extract clinically relevant biomarkers from a minimal number of medical images. By integrating multiple anatomical and functional measurements into a unified framework, comprehensive health assessment is possible. Moreover, we develop advanced extended reality (XR) systems for medical education, training, and procedure planning.
We develop intelligent assistive systems for blind and visually impaired persons based on image processing and deep learning. By utilizing generative models to simulate various environmental conditions, we achieve high robustness in algorithms for the real-time detection of key objects such as pedestrian crosswalks and signaling.
The group is developing virtual applications that would help people overcome obstacles in the environment with minimal dangers, e.g. educating children to cross the road in varying traffic density. Research is also being conducted in the direction of neural networks and their evolution through extended topology for the purpose of machine learning in games to reach the solution.
We explore the application of artificial intelligence in human-computer interaction through large language models, with emphasis on the Croatian language, education, and glotodidactics. We also work on multi-agent systems for autonomous task orchestration and explainable artificial intelligence that provides users with transparent and understandable decisions.
The group conducts research in advanced image processing and deep learning for analysis, enhancement, and compression of visual data, as well as their integration into intelligent visual systems for XR, interactive and virtual simulations, and real-world data analysis.
