Master Projects

Compute Graphics (infMPCG-01a, Sumer and Winter Term)

Abstract

This master project provides the opportunity to apply and advance the theoretical knowledge of computer graphics to a concrete practical problem. At the start of the semester students will pick concrete projects, for which they work together through the semester in small teams to achieve the goals.

Learning Objectives

Students will train to work in a team, to analyze the requirements for a practical project and to plan the steps to achieve the goals. They will also learn to tackle a complex problem with a focus on computer graphics and physical simulations and the use of the required software libraries.

A key goal of the project is to develop natural environments of either a forest or an underwater scene that can be explored with an agent. For a forest scene we want to use a drone that can navigate through the forest, while for the underwater scene a underwater robot will be implemented. The focus of the project can be on geometric modeling (e.g., trees, terrain, etc.), rendering (e.g., subsurface scattering, caustics, etc.), physics (e.g., fire, agent drift, etc.), game development (e.g. concept, user interfaces), as well as a cross-section of all topics. Projects with a focus on other scene setups are possible upon request.

Course Content

Advanced concepts of computer graphics, geometric modeling, physics-based simulation, and game design. The project will be implemented in Unreal Engine 5 with C++. Blender will be used for the geometric modeling of assets (if necessary).

Further Requirements

This master project targets students that have ideally completed the class Computer Graphics or those who have equivalent knowledge such that they understand advanced concepts of modeling and rendering.

Exam

Presentations including demonstration, report and the completed software system (incl. documentation).

Teaching and Learning Methods

Students will work on an individually defined project.

Literature

Real-time Rendering, Tomas Akenine-Möller, Eric Haines, Naty Hoffman, Angelo Pesce, Michael Iwanicki, Sebastien Hillaire, 4th Edition, Taylor & Francis
Fundamentals of Computer Graphics: International Student Edition, Steve Marschner, Pete Shirley, A K Peters/CRC Press; 5th edition, 2021

Additional Information

There are only a few slots available in this course. Please contact Sören Pirk directly by email (sp@informatik.uni-kiel.de) in case you are interested. Approval is mandatory before registering for the class. The first meeting for the project will be announced at the beginning of the semester.

Generative AI (infMPGAI-01a, Sumer and Winter Term)

Abstract

This master project provides the opportunity to apply and advance the theoretical knowledge of training deep neural networks and generative AI approaches to a concrete practical problem. At the start of the semester students will pick concrete projects, for which they work together through the semester in small teams to achieve the goals.

Learning Objectives

Students will learn to work on a complex problem with a focus on machine learning and generative AI. This includes the use of the required software libraries (Tensorflow, Pytorch, Python) and the required frameworks for training neural networks. A key goal of the project is to either use existing state-of-the-art neural network architectures, to develop novel architectures, or to apply AI models to applications toward medical diagnostics, manufacturing, and autonomous agents. Specifically, the projects are setup to leverage deep learning models for image generation, 3D shape processing, or learning models for time-series data. Students will also practice to work in a team, to analyze the requirements for a practical project, and to plan the steps to achieve the goals.

Course Content

Advanced concepts of Generative AI, including Generative Adversarial Networks, Diffusion Models, Domain Adaptation and Style Transfer, Neural Radiance Fields (NeRFs), and Synthetic Data Generation. The project will be implemented in Physthon or in conjunction with state-of-the-art rendering engines (e.g. Unreal Engine 5 with C++).

Further Requirements

This master project targets students that have ideally completed the class NNDL or GenAI or those who have equivalent knowledge such that they understand advanced concepts of modeling and rendering.

Exam

Presentations including demonstration, report and the completed software system (incl. documentation).

Teaching and Learning Methods

Students will work on an individually defined project.

Literature

Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, 2016, MIT Press
Generative AI - Teaching Machines to Paint, Write, Compose and Play, David Foster, 2019, O'Reily