HI Lights Seminar 4: The Extended Human Mind in Multi-Realities

Warmly welcome to HI Lights seminar 4 that explores extended reality (XR), artificial intelligence (AI), and robotics from interdisciplinary perspectives on Thu 9th of April, 2026 at TellUs Stage, Linnanmaa campus, University of Oulu. Bringing together internationally recognized experts and emerging researchers, the seminar highlights advances in computer vision, motion planning, neuroscience, and human–computer interaction.

Together, these perspectives deepen our understanding of how intelligent technologies extend human perception, cognition, and action across physical and virtual realities. The seminar is organized by the PROFI7 Hybrid Intelligence research program. Lunch and coffee are provided for the attendees.

Register here by Thu 2nd of April, 2026.

Programme

9:00 - 9:30
Welcome Coffee
Opening Remarks by Prof. Juho Kannala and Asst. Prof. Matti Pouke, Hybrid Intelligence programme, University of Oulu

9:30 - 10:30
Keynote: XTREME: Next-Generation Immersive Audio-Visual Mixed Reality Systems for Creative Production, Prof. Sami Brandt,D. Sc. (Tech.), Head of Research Group, Data Science, Machine Learning, Head of Research Group, Audio-Visual Computing, University of Copenhagen

10:30 - 11:30
Keynote: Combining Geometry and Learning in Vision, Viktor Larsson, Assistant Professor, Computer Vision and Machine Learning, Lund University.

11:30 - 12:00
Reconstructed Reality: Real-Time 3D Interfaces to Physical Spaces in Mobile Robotics and Telepresence, Eetu Laukka, Doctoral Researcher, University of Oulu

12:00 - 13:00
Lunch and networking

13:00 - 14:00
Plausibility of Intelligent Digital Characters in Human-AI Social Interactions, Chubo Zeko, Doctoral Researcher, Virtual Reality (VR), Hybrid Intelligence programme, University of Oulu.
Immersive perception, Evan G. Center, Postdoctoral Researcher, Extented Reality (XR), Hybrid Intelligence programme, University of Oulu

14:00 - 15:00
Keynote: Fundamental Challenges in Robotics and AI, prof. Steven M. LaValle, Computer Science and Engineering, University of Oulu

15:00 - 15:15
Closing remarks, coffee, and networking

Keynote abstracts:

XTREME: Next-Generation Immersive Audio-Visual Mixed Reality Systems for Creative Production, Prof. Sami Brandt, Head of the Audio-Visual Computing research group, IT University of Copenhagen

Mixed Reality (MR) is opening new possibilities for immersive media by combining physical environments with digitally generated content. However, creating truly compelling immersive experiences requires more than advanced displays and interaction devices—it demands deep integration of perception, audio-visual computing, and human–computer interaction. The Horizon Europe project XTREME explores how such technologies can be combined to build next-generation immersive audio-visual mixed reality systems for creative production. The core enabling technologies include spatial audio for immersive sound environments, advanced scene understanding for interpreting complex physical spaces, and markerless human motion capture for integrating performers into mixed reality environments.

Moreover, XTREME develops methods for audio-visual scene reconstruction and perceptual audio reconstruction, as well as AI methods for computational synesthesia, enabling cross-modal relationships between sound and vision. These technologies are integrated to enable shared and social experiences of performing arts events in mixed reality environments. The talk presents the technological vision of the XTREME project, discusses lessons learned from developing and integrating these components, and reflects on future directions for immersive media at the intersection of artificial intelligence, computer vision, spatial audio, and creative production.

Fundamental Challenges in Robotics and AI, prof. Steven M. LaValle, Computer Science and Engineering, University of Oulu

The field of robotics is wildly exciting and rapidly gaining worldwide attention, yet it is often an enigma in terms of its scope and scientific foundations. Throughout the decades, it has been variously viewed as an application field of more mature disciplines such as computer science (AI, algorithms, machine learning) and mechanical engineering (kinematics, dynamics, nonlinear control). Professor LaValle will argue that robotics has its own unique and growing scientific core, with deep questions and modeling challenges that should inspire new directions in computer science, engineering, and mathematics.

Combining Geometry and Learning in Vision, Assistant Professor Viktor Larsson, , Computer Vision and Machine Learning, Lund University

Geometric estimation has long relied on principled models and optimization, but many real-world settings challenge explicit modeling assumptions. In this talk, I will present recent work from my group and collaborators on integrating machine learning into geometric estimation pipelines. The core theme is that learning can complement, rather than replace, classical geometry: for example, it can model noise and uncertainty that are difficult to parameterize analytically, and it can strengthen estimation in ambiguous or underconstrained cases by introducing learned priors about scene structure. I will discuss examples spanning room layout estimation, visual localization, camera pose estimation, structure-from-motion, and image matching, and I will close with a preview of ongoing directions.

About the keynote speakers

Sami Brandt

Sami S. Brandt is Full Professor at the IT University of Copenhagen, where he heads the Audio-Visual Computing research group. His research focuses on computer vision, machine learning, and statistical methods for audio-visual data, with applications ranging from scene understanding and 3D imaging to immersive media technologies. He currently coordinates the Horizon Europe project XTREME, which develops next-generation mixed reality environments for art and culture. In recognition of his research contributions and interdisciplinary leadership, he received the first ITU Research Award in 2025. Prior to his current position, he held academic appointments at the ITU and the University of Copenhagen, and worked in industry as a Senior Mathematical Software Developer at 3Shape. He has also been appointed Adjunct Professor in the Machine Vision Group at the University of Oulu. He received his doctoral degree in 2002 from Helsinki University of Technology, where his research focused on geometric computer vision applied to electron tomography.

Viktor Larsson

Viktor Larsson is an Assistant Professor at Lund University, where he works on computer vision and machine learning. His research focuses on robust geometric estimation for 3D vision problems such as structure-from-motion, visual localization, SLAM, and dense geometry estimation, with a particular emphasis on combining deep learning with classical geometry-based pipelines. Before joining Lund, he was a postdoc and senior researcher in the Computer Vision and Geometry group at ETH Zurich.

Steven M. LaValle

Steven M. LaValle is Professor of Computer Science and Engineering, in Particular Robotics and Virtual Reality, at the University of Oulu. His research interests include robotics, virtual and augmented reality, sensing, planning algorithms, computational geometry, and control theory. In research, he is mostly known for his introduction of the Rapidly exploring Random Tree (RRT) algorithm, which is widely used in robotics and other engineering fields. In industry, he was an early founder and chief scientist of Oculus VR, acquired by Facebook in 2014, where he developed patented tracking technology for consumer virtual reality and led a team of perceptual psychologists to provide principled approaches to virtual reality system calibration, health and safety, and the design of comfortable user experiences. From 2016 to 2017, he was Vice President and Chief Scientist of VR/AR/MR at Huawei Technologies, Ltd. He has authored the books Planning Algorithms, Sensing and Filtering, and Virtual Reality.