Master's Thesis: Super resolution using machine learning at Imint

A recent trend in the smartphone industry is to add several cameras with different focal lengths, allowing the user to zoom while keeping the same resolution. Nevertheless, we are still limited to a relatively narrow zoom range, and often have to resort to digital zoom, which produces a lower resolution photo. Super resolution is a method that artificially increases the resolution after the capture, to try to alleviate the loss of resolution.

The objective of this thesis is to develop a super resolution algorithm using machine learning methods, which will include generating a dataset, setting up a neural network and training.

Attention: Often you need a pre-approval from your university or study counsellor, to be sure that projects or thesis found on MyCareer can be accepted as part of your education. Please contact the right entity in due time to ensure that you're picking the right project.