This group will address topics related to image processing and computer vision, and will mainly focus on problems related to new formats of image/video such as Light Field images; Depth-map based images, and 360 panorama videos. Furthermore, the group aims to work on Depth-map estimation and applications. This group will investigate the use of state-of-the-art Deep Learning approaches in the abovementioned fields, and for other practical applications.
Human brain consumes, roughly, 20% of human-intake of energy, and a considerable amount of this energy goes for vision tasks, thus, it is reasonable to expect an expansion of computer vision applications, including image/video understanding/sharing and exploitation. This explains why Cisco forecasts a huge increase in video content in the coming years: “It would take an individual more than 5,000,000 years to watch the amount of video that will cross-global IP Networks each month in 2020”. Needless to say that the activities of this research group will benefit and compliment the activities of other groups in the University.