The Master’s programme consists of compulsory courses, electives, and a Master’s thesis.

First period

Scientific perspectives on GMT (compulsory)

There is no content available for this course.

Motion and manipulation

Motion and manipulation are key issues in the field of robotics and automation, but they also play a major role in virtual environments and games. In this course models and planning problems for tasks that involve motion or manipulation are studied. The course covers topics from kinematics, which studies motions without taking their causes into consideration. The study of manipulation concentrates on kinematic models for articulated structures such as arms, models for grasp analysis based on velocities and forces, and on simple non-prehensile forms of manipulation such as pushing. Special attention is given to industrial automation as an example of manipulation planning. Geometry is a major parameter in the definition, modeling, and planning of manipulation and motion tasks.

Multimedia retrieval

Multimedia retrieval is about the search for and delivery of multimedia documents: images, sound, video, 3D scenes, and the combination of these. This course deals with the technical aspect of multimedia retrieval such as techniques, algorithms, and data structures for search query formulation, media feature description, matching of descriptions, and indexing.

Optimization and vectorization

Writing high-performance applications and increasing the performance of existing applications is a rewarding process, that typically yields improvements of 10x or more. In this course, a structured approach to program optimization is presented. The main factors that determine program performance are:
* Algorithm efficiency;
* The memory / cache hierarchy;
* Thread-level and instruction-level parallelism (vectorization), including SIMD.
These will be explored in detail, in a practical, hands-on manner.
The focus will be on CPU code, but optimization using GPUs and GPU performance characteristics will be covered as well.

Second period

Geometric algorithms

There is no content available for this course.

Pattern recognition

In this course we study statistical pattern recognition and machine learning.

The subjects covered are:

General principles of data analysis: overfitting, the bias-variance trade-off, model selection, regularization, the curse of dimensionality.
Linear statistical models for regression and classification.
Clustering and unsupervised learning.
Support vector machines.
Neural networks and deep learning.

Knowledge of elementary probability theory, statistics, multivariable calculus and linear algebra is presupposed.

Advanced graphics

In this course various subjects related to rendering are discussed, with a focus on knowledge and techniques useful for (future) games and game-tools. Subjects include global illumination approaches, (anti-)aliasing, shadow mapping techniques, dynamic lighting architectures and graphics hardware.

Sound and music technology

Sound and music provide powerful ways for impacting the human experience involved in the engagement with games and media. In this course, you will learn how to apply and develop computational methods to extract, process and utilize music information from digital sound and music in the context of newly emerging research areas within games and media. You will learn how sound and music information is crucial for the human experience, and how the computational modelling of sound and music contributes to the enrichment of this experience in games and media. This encompasses that you will get to know both basic concepts on how human listeners extract, make sense of and give meaning to information from sound and music, and how these basic concepts are used, researched and applied through computational technology.The course is structured around three main modules:
A: Sound and music for games
B: Analysis, classification, and retrieval of sound and music for media
C: Generation and manipulation of sound and music for games and media
The course will cover key topics for sound and music technology in the context of games and media, such as interactivity and immersion in games through sound and music (A), classification and retrieval of similar musical objects in multimedia (B), and the utilization of the emotional and affective qualities of music in games and media (A, C). You will learn what specific technologies are developed and required within these key topics, such as automatic pattern discovery, sound separation, voice separation, automatic segmentation, and feature extraction and manipulation (B). For studying, discussing and employing these technologies you will get to know different representation forms of music information in audio and symbolic data (A), different musical dimensions such as melody, rhythm, harmony, timbre and loudness (A, B), and how they are modelled through computational features (A, B, C). Moreover, you will learn about different general strategies for developing computational models for sound and music processing, such as model-based versus data-driven approaches, and about the challenges of evaluating these models.

Third period

Computer vision (compulsory)

The goal of computer vision is recognize and understand the world through visual information such as images or videos. This course is about the algorithms and mechanisms to extract and classify information from images and video. The course combines theory and practice, with two themes: multi-view reconstruction and CNN image/video classification.

Game physics

An immersive game experience requires realistic game physics. In this course a number of topics regarding game physics are covered. These topics include rigid body physics, numerical integration methods, collision detection and collision resolution, soft body physics, physics engine design and implementation.

Multimodal interaction

This course covers multimodal (multisensory) perception and interaction.
The course starts with a discussion of the fascinating world of human visual, auditory and tactile perception and the use of its potential in designing novel interfaces for interacting with virtual worlds.
Furthermore, augmented reality is covered as one particular example of multimodal interaction. In the practical part, students will apply the theoretical background of multimodal perception and multisensory input to concrete state-of-the-art examples (e.g., from virtual or augmented reality).

Fourth period

Mobile interaction

Mobile devices, such as smart phones and tablets, have become as powerful as traditional computers, often replacing them for various tasks. Yet, interacting with them remains challenging due to issues such as limiting form factor, mobile context, etc. On the other hand, it is exactly this form factor, context, and other characteristics of mobiles that provide us with new and exciting opportunities for alternative usages. Examples range from innovative mobile games, to mobile AR (augmented reality) applications. In this course, we will have a closer look at standard interaction with mobiles (e.g., via touch screen; including potential issues as well as opportunities), address new approaches, and look into related current and future research -- including wearable devices (e.g., head mounted displays, such as Google Glass, wristbands and smart watches, such as the Apple Watch). Concrete application domains include mobile gaming and mobile video.

Computer animation

This course discusses a variety of topics related to computer animation, such as: motion capture, blending, (inverse) kinematics, physics-based animation, and more. Furthermore, a number of guest lectures by experts in the field is part of this course.

AI for game technology

In this course the use of AI techniques in games is explored, for instance in serious gaming and training. Distributing game control over several independently operating agents is discussed, several path-planning techniques useful for computer games are investigated, and dynamic re-planning algorithms useful for dealing with dynamic environments are described. Furthermore, machine learning techniques such as evolutionary algorithms with neural networks are discussed, as well as some techniques and solutions for multi-agent cooperation.body { font-size: 9pt;

Crowd simulation

There is no content available for this course.