Abschlussarbeiten

Hier am Institut bieten wir laufend hochaktuelle Themen für Abschlussarbeiten an. Die hier aufgeführten Themenvorschläge sind in der Regel eng mit dem Arbeitsgebiet des betreuenden Assistenten verknüpft und ermöglichen Ihnen die Mitarbeit an zukunftsweisenden Technologien. Bei Interesse an einem der Vorschläge oder an einzelnen Themengebieten freuen sich die jeweiligen Assistenten über Anfragen.

Bei allgemeinen Fragen zur Koordination von Abschlussarbeiten steht Ihnen Dominik Mehlem gerne zur Verfügung.

Hier ist eine Liste unserer aktuell angebotenen Themen:

Point Cloud Compression

A point cloud is a three-dimensional data structure which comprises geometry and associated attributes. The general idea of point cloud compression is to find a representation of a point cloud which is less data exhaustive than the original raw point cloud whilst still preserving the best possible quality. The research at the institute focuses mostly on Machine-/Deep-Learning based methods. Currently, within the standardization group MPEG(Moving Picture Experts Group) an AI-based standard is being developed.

AI-based Point Cloud Attribute Compression	Dominik Mehlem M.Sc.
In recent years, first approaches for neural network based approaches showed to outperform the traditional approaches from a RD-based perspective. Whilst learning-based geometry compression shows to outperform traditional methods, this is so far not the case for learning-based methods for attribute compression. The objectives of this master’s thesis lie in the rigorous scientific examination of attribute coding for dynamic point cloud sequences using neural networks. In this context, the following aspects are to be implemented, investigated, and, where applicable, corresponding questions addressed: A comprehensive overview of existing AI-based methods for attribute coding should be provided. This includes an extensive literature research and analysis of the current state of research. An appropriate training set with a suitable train/test/validation split should be assembled. As a reference basis, an implementation of the currently developed MPEG AI-PCC standard for point cloud compression will be used. The implementation will be provided. Implementation and analysis of the most promising approach. Optimization and improvement of the initial method. (Optional) Complete performance analysis of the own approach compared to classical standards and AI approaches; analysis of individual aspects for performance gain. As further questions arise during the work, these should be documented and answered as well. The approach of this master’s thesis is based on a precise analysis of the points mentioned above. Implementations are carried out in Python and C++. The thesis shall be written in \LaTeX.
Suitable only for Master theses.

AI-based Point Cloud Attribute Compression

Dominik Mehlem M.Sc.

Example frames of dynamic point cloud sequences

In recent years, first approaches for neural network based approaches showed to outperform the traditional approaches from a RD-based perspective. Whilst learning-based geometry compression shows to outperform traditional methods, this is so far not the case for learning-based methods for attribute compression.

The objectives of this master’s thesis lie in the rigorous scientific examination of attribute coding for dynamic point cloud sequences using neural networks. In this context, the following aspects are to be implemented, investigated, and, where applicable, corresponding questions addressed:

A comprehensive overview of existing AI-based methods for attribute coding should be provided. This includes an extensive literature research and analysis of the current state of research.
An appropriate training set with a suitable train/test/validation split should be assembled.
As a reference basis, an implementation of the currently developed MPEG AI-PCC standard for point cloud compression will be used. The implementation will be provided.
Implementation and analysis of the most promising approach.
Optimization and improvement of the initial method.
(Optional) Complete performance analysis of the own approach compared to classical standards and AI approaches; analysis of individual aspects for performance gain.

As further questions arise during the work, these should be documented and answered as well. The approach of this master’s thesis is based on a precise analysis of the points mentioned above. Implementations are carried out in Python and C++. The thesis shall be written in \LaTeX.

Suitable only for Master theses.

Virtual Human’s Behavior in Social Mixed Reality

Virtual humans are digital representations of people. One of the main challenging aspects is that they act and move in a coherent and believable manner, adhering to the affordances of AR or VR environments. Here, virtual human’s fidelity can be explored in three major aspects, physical (how they look, sound, and move), functional (how they react and interact with the environment, which is particularly important for AR), and psychological (the level of authenticity in the emotions they display). We offer several master's theses that can address one or several of these aspects. The students interested in pursuing these topics should have or be willing to acquire strong skills in 3D design and development (Unity, Unreal, Blender, Mixamo) and should be interested in conducting an empirical study and familiarizing with research methods in human-computer interaction.

Suitable for Bachelor and Master theses. Contact person: Dr.-Ing. Stephanie Gabriela Arévalo Arboleda

Subjective Quality Assessment of AI-based Videos

We offer theses in the field of quality assessment of AI-generated and AI-processed videos. Topics include the design of subjective user studies, the analysis of subjective data, and the development of evaluation models, with the goal of algorithmic prediction of human perception. Students gain practical experience with modern video generation or processing techniques, the design of experimental studies, and statistical data analysis. Projects can be tailored to individual interests and prior knowledge.

Suitable for Bachelor and Master theses. Contact person: Julius Prenzel M.Sc.