Artificial Intelligence

Blog Post
MOVIDA Begins: A New EU-Co-Funded Project Exploring AI and Dance
We are excited to announce the launch of MOVIDA — "Movement and Virtual Intelligence for the Development and Accessibility of Artists and Audiences", a new three-year European cooperation project co-funded by the Creative Europe Programme of the European Union.
Blog Post
MODINA: Reflecting and Moving Forward
From 23 to 25 January 2026, the MIREVI team at the university of Applied Sciences Düsseldorf hosted a three-day closing event for the EU-funded project MODINA – Movement, Digital Intelligence and Interactive Audience in collaboration with with tanzhaus nrw.
Blog Post
Fast Forward at Ludwig Forum Aachen
In January we took part in the program “Fast Forward” at Ludwig Forum Aachen with two interactive installations and a talk. In the context of Shu Lea Cheang’s exhibition KI$$ KI$$, the event explored urgent questions about whether AI will become a curse or a blessing for society—and how art can help negotiate these uncertain futures.
Blog Post
MODINA Exhibition
The exhibition brings together selected works and artistic research developed within the MIREVI context, alongside contributions from associated artists. It foregrounds experimental approaches at the intersection of movement, digital intelligence, and interactive systems. Rather than positioning dance solely as a stage-based practice, the exhibition invites visitors to encounter movement as data, interface, environment, and embodied interaction—unfolding across installations, tracking systems, and performative setups. Video documentation complements the exhibition, providing insight into artistic processes, research trajectories, and the development of the presented works. Rather than functioning as a retrospective, the exhibition focuses on questions that continue to shape contemporary choreographic and artistic research: How does technology transform choreographic thinking and bodily behavior? In what ways can digital systems act as collaborators, constraints, or counterparts rather than mere tools? How might audiences experience movement through interactive, hybrid, or speculative formats?
Publication
Precious Camouflage - Artistic Research for the Creation of a Dance Piece with Humans and AI
This paper presents the layout of and research behind the dance performance Precious Camouflage, which explores the interplay between human movement and artificial intelligence (AI) within a museal space. The work stages four AI systems that interact live with a contemporary dance ensemble and the audience, critically examining themes of agency, surveillance, interpretation, and body politics.
Blog Post
Precious Camouflage at Expanded 2025
Charlotte Triebus, Ivana Druzetic-Vogel and Chris Geiger presented "Precious Camouflage" at the Expanded Conference on the 5th of September 2025.
Blog Post
The Field/Gaitless
In March and April 2025 MIREVI has been supporting the conceptual and technical development of the project „The Field / Gaitless“ by MODINA residency artists Marko Milić and Uroš Krčadinac.
Blog Post
TEMPS D'IMAGES Opening Weekend
January 2025 marks the 20th edition of Temps d'Images, the festival for dance and technology at tanzhaus nrw. This year MIREVI presents two installations at Temps d'Images: "Precious Camouflage - OS" by Charlotte Triebus x MIREVI and "The Poetry of Motion" by Joelle Schonhoff, co-produced by MIREVI.
Blog Post
Guest Performance of Precious Camouflage at ZKM Karlsruhe
In June, Charlotte Triebus and MIREVI premiered Precious Camouflage at tanzhaus nrw in Düsseldorf. Last week the project was shown as a guest performance at ZKM in Karlsruhe.
Blog Post
Invitation to Workshop "KI-basierte Energieoptimierung"
On the 5th of November 2024, ZIES and MIREVI present the “Fast Energy Design Tool” in cooperation with DITEC as part of a workshop on AI-based energy optimisation. Registration is open until 31.10.2024.
Blog Post
Precious Camouflage Premiere
In June 2024, Charlotte Triebus and Mirevi presented Precious Camouflage, a cooperative dance piece for human and AI agents at Tanzhaus NRW.
Blog Post
persona fractalis II
The immersive media installation personal fractalis II (pf.2) invites visitors to let themselves be drawn into an immersive generated world of fractals - the user explores freely in this utopian environment or embarks on a journey of discovery curated by the author and artificial intelligence.
Publication
Unmasking Communication Partners: A Low-Cost AI Solution for Digitally Removing Head-Mounted Displays in VR-Based Telepresence
Face-to-face conversation in Virtual Reality (VR) is a challenge when participants wear head-mounted displays (HMD). A significant portion of a participant’s face is hidden and facial expressions are difficult to perceive. Past research has shown that high-fidelity face reconstruction with personal avatars in VR is possible under laboratory conditions with high-cost hardware. In this paper, we propose one of the first low-cost systems for this task which uses only open source, free software and affordable hardware.
Blog Post
Towards Face-to-Face Telepresence Applications in Virtual Reality with Generative Neural Nets
Philipp Ladwig held a talk at the 17th GI VR/AR workshop about our research in the area of telepresence in virtual reality applications. The associated paper written by Philipp Ladwig and Alexander Pech under the guidance of Prof. Dr. Christian Geiger received the "Best Paper" award.
Publication
Smart Object Segmentation to Enhance the Creation of Interactive Environments
The objective of our research is to enhance the creation of interactive environments such as in VR applications. An interactive environment can be produced from a point cloud that is acquired by a 3D scanning process of a certain scenery. The segmentation is needed to extract objects in that point cloud to, e.g., apply certain physical properties to them in a further step. It takes a lot of effort to do this manually as single objects have to be extracted and post-processed. Thus, our research aim is the real-world, cross-domain, automatic, semantic segmentation without the estimation of specific object classes.

No posts could be found.