Teaching
Winter Term
Computer Graphics (infCG-02a)
Abstract: Computer Graphics enables the generation of visualizations that can be used in a variety of domains and applications, such as movies and games, manufacturing, architecture, and in research. Due to recently introduced concepts, such as the Metaverse and Digital Twins, 3D computer graphics has gained a considerable amount of momentum. Key goals of Computer Graphics are to develop algorithms for rendering images, for modeling the 3D geometry of objects and scenes, and for generating simulations and animations.
Summer Term
Generative AI (infGAI-01a)
Abstract: This lecture is dedicated to developing an understanding of generative AI models with a focus on visual computing. The lecture will introduce the diverse applications of generative AI, ranging from generating new data samples and using generative architectures for data augmentation to highlighting how these technologies are revolutionizing multiple industries. By the end of the lecture, attendees will gain an understanding of generative AI, equipped with the knowledge to critically assess its applications. This lecture is designed to cater to a wide range of students, from BA and MSc to students of other courses.
Winter Term
Time Series Predictions with Sequential Neural Networks (infBSemZsnN-01a)
Abstract: This seminar addresses the learning of models for the analysis and prediction of time series. Time series are temporally ordered data points that are collected, for example, hourly, weekly, or annually. The analysis and prediction of time series are of great interest in a variety of fields (e.g., economics, remote sensing, robotics, meteorology). Time series models aim to enable the prediction of trends, which allow statements to be made about the future development of observations.
Winter/Summer Term
Master Project - Computer Graphics (infCG-02a)
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.
Winter/Summer Term
Master Project - GenerativeAI (infMPGAI-01a)
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.
Below you can find a selection of open thesis projects that the VCAI group is offering. Please reach out to Prof. Sören Pirk if you are interested in one of the topics. You can also propose your own projct.
Generating Evacuation Tours through Deep Reinforcement Learning
[Type: Master Thesis, Focus: Computer Graphics, Machine Learning]
Digital twins of indoor scenes are today more and more available in several forms such as 3D models, games and through building information modelling tools. In this project we want to leverage 3D building models for evacuation safety where evacuation tours are automatically generated for the scope of training people on evacuation paths in case ofemergency. The computed evacuation tours are used to guide and train people in case of emergency evacuation. Such tours could also be enhanced with inclusive features (e.g., an automated generation of tours that include a vocal description of what is seen, so that could be used to help people with visual impairments learning about evacuation paths). This project will focus on developing a methodology for automating the generation of trajectories of evacuation paths based on deep reinforcement learning. An agent is trained to learn how to automatically control a camera to generate an evacuation path that can be used for safety purposes.
Modeling and Rendering of Underwater Environments
[Type: Bachelor or Master Thesis, Focus: Computer Graphics]
This project aims to create photorealistic underwater scenes that can be explored with a robotic agent. The core focus is on developing sophisticated computer graphics techniques to accurately simulate underwater optical properties like light refraction, scattering, and caustics, ensuring detailed and lifelike visuals. The project also involves programming a robotic agent to move through these scenes, interact with underwater terrain, and engage with marine flora and fauna, emulating real-life underwater exploration.
Uncertainty Visualization for AI-based Segmentations of Medical CT Volumes
[Type: Bachelor or Master Thesis, Focus: Computer Vision, Medical]
Various organs of the human patient can be segmented from CT scans and the corresponding greyscale axial views. AI models already achieve a high accuracy in the segmentation, but still need to be corrected. Instead of a binary classification mask as output, a heatmap may display the certainty of the segmentation and improve the understandability of the model.
Effect of the Patient's Rotation Angle on Tissue Deformation in CT Volumes
[Type: Bachelor or Master Thesis, Focus: Computer Vision, Medical]
While medical CT scans are generally taken in a supine position (lying on the back), during the actual surgery, patients are often positioned on their side. This leads to a deformation of internal organs so that their position does not match the CT scan anymore. The elasticity of various organ types may be estimated from tissue characteristics and used to predict absolute movement under the influence of gravity.
Semantic Segmentation of Outdoor Scenes
[Type: Master Thesis, Focus: Computer Vision]
This project aims to develop a deep learning model for semantic segmentation in outdoor environments, with a specific focus on identifying and classifying various types of vegetation such as trees, grass, shrubs, and other plant species. The student will work with datasets of outdoor images and leverage convolutional neural networks (CNNs) or other machine learning models to differentiate vegetation from non-vegetation areas. The outcome of the project will be a tool that can accurately map vegetation in outdoor scenes, potentially useful for applications like environmental monitoring, agriculture, and urban planning.
Randomized Look-Up Data Structures for Spatial Data
[Type: Bachelor or Master Thesis, Focus: Computer Graphics]
The goal of this project is to investigate how randomization can be used to engineer efficient data structures for queries on spatial data. Initially, a literature research should be conducted to compile an overview of what the state of the art is. Based on this, data structures that have only been proposed theoretically should be implemented or entirely new data structures should be developed and implemented. Experiments should then be conducted comparing the performance to that of conventional data structures (e. g. Kd-trees, octrees). Optionally, these newly developed data structures could make use of learned biases to make random decisions which might yield further performance improvements.
Ongoing
Summer 2025 (SS2025)
Geometric Modeling of Harbor Scenes and Path Planning for Boats (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M.Sc. Nikolas Schwarz
Follow Me: Vision-Based Person Following for Autonomous Robot Navigation
Supervisors: Supervisors: Prof. Dr. Sören Pirk, B.Sc. Anton Wagner
Object Search and Localization: Autonomous Detection of Target Items in Indoor Environments (Bachelor Thesis)
Supervisors: Supervisors: Prof. Dr. Sören Pirk, B.Sc. Anton Wagner
Energy-based Procedural Modeling of Botanical Trees (Bachelor Thesis)
Supervisors: Supervisors: Prof. Dr. Sören Pirk, M.Sc. Nikolas Schwarz
Advanced Procedural Modeling of Leaves for Botanical Trees (Bachelor Thesis)
Supervisors: Supervisors: Prof. Dr. Sören Pirk, M.Sc. Nikolas Schwarz
Interactive Visualization for Contour Placement in Intercranial Aneurysms (Master Thesis)
Supervisors: Prof. Dr. Sören Pirk, Prof. Dr. Sylvia Saalfeld
Completed
Fall 2024 (WS2024/2025)
Advanced Visual Augmentation of Conversations with Language-based Rasoning (Master Thesis)
Supervisors: Prof. Dr. Sören Pirk
Optical Music Recognition with AI (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Nikolas Schwarz
Automated Generation of Synthetic Data for Document Understanding Tasks (Master Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Marten Finck, M. Sc. Helge Wrede
Adding Document Artifacts using Generative Artificial Intelligence (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Marten Finck
Generierung von Röntgenbildern mit Hilfe von Diffusionsmodellen (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Marten Finck
Classification of binary 3D-Files (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Nikolas Schwarz
Conversation Amplification through Language-based Reasoning and Generative Visual Content Creation (Master Thesis)
Supervisors: Prof. Dr. Sören Pirk, Prof. Dr. Hans-Christian Jetter
Summer 2024 (SS2024)
GAN-based Generation of Terrain / Erosion (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Nikolas Schwarz, M. Sc. Sarker Miraz Mahfuz
Influence of Animal Behavior on Predator Prey Systems (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Nikolas Schwarz, M. Sc. Sarker Miraz Mahfuz
Analysis of a Evolutional Reinforcement Learning Predator Prey Simulation (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Sarker Miraz Mahfuz, M. Sc. Helge Wrede
Automating Espresso Grinder Adjustments Using Deep Learning Techniques (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Nikolas Schwarz, M. Sc. Marten Finck
Training Neural Networks to Play Chess Like Games (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Helge Wrede, M. Sc. Sarker Miraz Mahfuz
Guiding Stable Diffusion with a 3D Editor (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Nikolas Schwarz
A Multi-task Downstream Task for Biomarker Identification Using Medical Chest X-ray Images (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Marten Finck
Anomaliedetektion mittels Machine Learning auf Geodaten für das Asset Tracking (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, Dr. Lars Schwabe
Testing, Monitoring and Analysis of AI-based Chat Bots (Master Thesis)
Supervisors: Prof. Dr. Sören Pirk, Jan Monica
Fall 2023 (WS2023/2024)
Predicting Gaussians: 3D Scene Reconstruction using Transformers (Bachelor Thesis)
Supervisors: Prof. Dr. Sören Pirk, M. Sc. Helge Wrede