Ankita Atrey
12 February 2025 · 5 min read
In December 2024, Stefanie Zollmann commenced her position at Aarhus University as an Associate Professor within the Ubiquitous Computing and Interaction group . Her research primarily centers on the exploration of integrating methodologies from Computer Graphics, Visualization, and Computer Vision to intricately embed digital information within our environment. Stefanie serves on the Editorial Boards of Transactions on Visualization and Graphics (TVCG) and Computers & Graphics. She also chaired the program committees for the IEEE ISMAR conferences in 2019 and 2020, as well as the IEEE VR 2024, both of which are top conferences in AR and VR research, in addition to being a member of the IEEE ISMAR Steering Committee.
Academic Background
Before joining Aarhus University, Stefanie co-led the Visual Computing Otago research group at the University of Otago, where she focused on the intersection of Computer Graphics, Computer Vision, Machine Learning, Visualization, and Human-Computer Interaction. Her work centered around eXtended Reality (XR) for sports and media, situated visualization techniques for Augmented Reality, and novel methods for capturing content for immersive experiences. Prior to starting her position at the University of Otago in 2016, Stefanie worked as a Senior Developer at Animation Research Ltd in Dunedin, New Zealand and gained experience at Daimler and Graz University of Technology. In 2013, Stefanie earned a PhD in Computer Science from Graz University of Technology in Austria. She graduated in 2007 as a "Diplom-Mediensystemwissenschaftlerin" from the Bauhaus University in Weimar, Germany.
Could you explain your current research focus?
My current research focuses on different aspects of XR and its applications in and implications on diverse fields such as sports, health, industrial applications, and everyday usage scenarios. AR and VR offers the potential to transform sports and health applications by enhancing spectating, facilitating learning, and supporting rehabilitation. The research investigates how AR can enrich the spectator experience with real-time, customized overlays of game-related content and training location-specific neural networks for advanced localization and tracking in large-scale environments such as stadia. The goal is to deliver immersive, interactive, and informative viewing experiences. Recently, we expanded to explore AR and VR in training and education, providing personalized tutorials and insights to enhance understanding and engagement with sports. It also extends to physiotherapy and rehabilitation, using immersive technology to aid recovery, improve motor performance, and support health and fitness goals. We also investigate casual capture for VR and AR, combining traditional computer graphics and vision, neural rendering, and diffusion models for interactive image synthesis to create immersive VR experiences from 2D footage. Additionally, we aim to advance everyday AR by using machine learning and trained networks to develop continuous, adaptive, and multi-purpose AR systems, enabling dynamic, context-aware experiences that seamlessly integrate digital content into the real world.
What challenges have you encountered in your research?
One of the main challenges has been how to make sense of large amounts of data, especially when trying to overlay information like 3D models or track data in real-time. There’s also the issue of personalization—how to ensure the information presented isn’t overwhelming to the user, and how to tailor it to their specific needs. Another challenge has been designing systems that are easy for people to interact with, especially in complex environments like construction sites or medical applications. Making things intuitive while dealing with large datasets is always a bit tricky.
Could you give an overview of the visual computing course you're designing, and the key learning outcomes students can expect?
I am thrilled to be designing this course alongside Prof. Tobias Langlotz. It's been an amazing collaboration, blending our ideas to create something truly innovative. This course focuses on the high-demand skills of computer vision and computer graphics. The reason we combine these topics is that both involve similar processes, and one can think of them as the inverse of each other: Computer vision is taking a graphical representation – usually one or several images, and computer a scene description, while computer graphics takes a scene description and renders a graphical representation. In computer vision, you’ll learn about camera models, geometry, and how to extract scene information. In computer graphics, you’ll learn how to efficiently render complex graphical representations.
We initially cover the fundamentals including necessary mathematical models but also discuss different rendering technologies, shader programming, and how Machine Learning and AI is revolutionizing the field. These skills are highly relevant in areas like game development. Virtual- and Augmented Reality but also the digital movie industry. We’re excited to offer this course, as it’s not currently available here and will provide valuable skills for students.
What do you like to do outside of work?
Outside of work, I enjoy outdoor activities like surfing, hiking, biking, and skateboarding. Occasionally, I like to work on crochet. I am a big coffee lover too, so I love discovering new coffee spots and spending quality time with my family.
What makes Aarhus University the ideal choice for you?
We visited the department in 2022 for a research visit, and it was a very positive experience. I loved the inspiring atmosphere here, and everyone I met was friendly. Aarhus University has an excellent academic reputation, and Denmark offers a great work-life balance. The research environment here is highly supportive of fundamental research, which aligns closely with my interests.
