Dense Image Matching with Transformer
Student should be able to use a suitable programming language, e.g. PyTorch
The student will initially revise the existing literature on image matching algorithms using CNN as backbone. The use of already existing code and available datasets to train these algorithms will be the starting point of the work. As starting point, the student will focus on the use of existing algorithms in order to familiarize with the algorithms. Then, some provided datasets of airborne UAV images will be used for the same purpose. In this case, the images (as well as the training point clouds) will be provided by the supervisors. Then, the student will need to develop new deep learning algorithm, e.g. novel Transformer-based architecture. The main challenges will be to develop, implement and train the algorithms. The expected output will be a trained Transformer able to provide a depth map from a set of overlapping images.
The main objective of this research is re-visiting dense image matching with modern AI methods. Dense image matching is the core part of Photogrammetry. It has been done by Semi-global matching for the last decade. In light of the success of modern AI algorithms, this research will investigate new deep learning algorithm, e.g. novel Transformer-based architecture, for dense image matching.