zur Startseite

Masterarbeit

Dense Light-field Dataset for Deep Learning Application
Betreuer M.Eng. Trung Hieu Tran
Prüfer Prof. Dr.-Ing. Sven Simon
Ende
Beschreibung

Applying deep-learning (DL) to Light-field (LF) image processing has currently become a very active area of research. Many difficult problems in LF image processing such as disparity estimation, super-resolution, object detection,... has been successfully solved by applying DL techniques. More sophisticated DL architectures bring better results but at the same time require a large amount of training data which was known to be the main obstacle in this research area.

This master thesis aims for building a synthetic light-field dataset for supporting DL applications. The two following tasks will be mainly covered in this thesis: Studying LF geometry and applying rendering tools such as POVRay, Blender to generate LF dataset with well-labeled data; Benchmarking state-of-the-arts DL algorithms on the proposed dataset. The duration of the thesis will be 6 months (full-time).

Prerequisites:

  • Experience with Matlab/Python
  • Experience with deep learning frameworks (PyTorch/Tensorflow)

Contact:

Trung Hieu Tran (trung.hieu.tran@ipvs.uni-stuttgart.de)

Download PDF