Topics in the area of combining dictionary learning / sparse coding with video coding Jens Schneider M.Sc.

The field of dictionary learning and sparse coding has raised more and more interest in the last years. State of the art results for various problems of signal processing were obtained by these methods. More precisely, dictionary learning shows good performance for denoising, inpainting and super-resolution. Therefore, it is assumed that dictionary learning / sparse coding methods can also be used for compression of video content. In possible thesis work it will be investigated how sparse coding methods can be introduced into the well known hybrid video coding scheme consisting of intra prediction, inter prediction and residual coding.

Possible topics in this area lie in the field of:

  • Dictionary learning / sparse coding for intra prediction in video coding
  • Dictionary learning / sparse coding for dynamic resolution conversion coding
  • Optimization of sparse coding algorithms

Every thesis will require implementations in MATLAB or C++. Therefore, a high motivation and interest for software programming is recommended.

Masterthesis: Higher order motion models for motion compensation in 360° video Johannes Sauer M.Sc.

Current motion compensation methods have been developed for conventional video, in which a video frame can be seen as the projection of a 3D scene onto a plane. In 360° video a frame is the projection of the surface a sphere. Since this surface is not even, distortions are introduced into the MC process. While affine motion compensation is in investigation for current video codecs, the distortions occurring in 360° video require even more general motion models. In this thesis In this thesis it shall be investigated if higher order motion models or an approximation with an affine motion model can be used to treat the distortion in motion compensation for 360° video.

Basic programming skills ( C++, Matlab ) are required. Prior knowledge of video coding and image processing is helpful.

Masterthesis: Optimized scanning order for Intra Coding Johannes Sauer M.Sc.

Current video coding uses a scanning order for CTUs which is fixed. Starting at the top left frame border a z-scan is performed, a row is processed completely before the next row is started. The scanning order determines from which sides samples are available for Intra prediction. In this thesis the performance of alternative scanning orders should be investigated. What is the optimum scanning order? Is it beneficial to change the order flexibly by signaling it? Can the optimum order be determined from the frame characteristics?

Basic programming skills ( C++, Matlab ) are required. Prior knowledge of video coding and image processing is helpful.

Masterthesises in the area of neural network based video intra prediction Maria Meyer M.Sc.

A fundamental part of each image or video coding algorithm are methods that try to predict parts of the frames or images based on the information that was coded beforehand in order to significantly reduce the redundancy. These methods can be classified into two basic categories: Inter prediction methods that use information from previous frames and intra prediction methods that only information from the local neighborhood within the same frame.
While conventional intra prediction methods determine the prediction based on a set of linear filters, some recent proposals started to use neural networks for this purpose. In particular it is possible to train a convolutional neural network (CNNs) to predict a block based on its local neighborhood and use the result as an additional prediction option in a video coder. Unlike the conventional methods, these CNNs can usually adopt to nonlinear edges and textures. However, there is still much room for improvement in the training techniques and inference optimization processes.
There are frequently master thesis topics coming up in this general area. Please ask, if you are interested in the general area.