Deep Learning for Video Compression
This project will firstly examine and analyse deep learning techniques particularly in the context of their applicability to ultra high resolution (4K/8K) image/video compression. The project will look into the coding efficiency and bit-rate optimisation of deep learning techniques compared with standard compression methods e.g. HEVC. Students with prior project experience in image/video compression would be particularly suitable, but those opting to do research area with no previous exposure to any project work in the field will also be considered. Some prior knowledge of basic signal/image processing fundamental principles would certainly be an asset. The project will very much adopt an innovative approach aiming to push the boundaries of the state of the art in the field and will therefore have a drive for publications as well as attraction of industrial interest.
This is a self funded project
Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. Recently the UK Government made available the Doctoral Student Loans of up to £25,000 for UK and EU students and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.)