Introducing ReTiNA-Cinema: Real-Time Neuro-Augmented Cinema via Generative AI
Antoine Bellemare-Pepin, Philipp Thölke, Yann Harel, Mar Estarellas, Karim Jerbi
Abstract
Generative artificial intelligence (AI) is currently revolutionizing content creation across various media. Between those who fear it will replace human creativity and those who regard it solely as a tool, many in the creative industries are beginning to view generative AI as a collaborator. Yet interaction with these systems often relies on discrete, turn-based prompting that can interrupt flow and constrain expression to symbolic text. We explore physiological signals as a source of continuous adaptation without explicit commands, as a path toward embodied co-creation. This paper presents ReTiNA-Cinema, a methodological proof-of-concept that integrates electroencephalography (EEG) with generative AI to enable physiologically guided visual modulation of cinematic material. By linking physiological activity to the evolving appearance of a film, the system provides a basis for exploring embodied sense-making, in which viewers' bodily responses contribute to shaping the sensory experience through which they interpret the unfolding scenes. The system combines real-time EEG signal processing with a generative AI pipeline based on Stable Diffusion Turbo for frame-level image transformation. Single-user and two-user configurations map EEG-derived features to prompt selection and transformation strength. ReTiNA-Cinema offers a framework for exploring how the physiology of viewers might influence a film's visual presentation, extending the possibilities for participation in cinematic experiences and storytelling. This system raises questions about the effects on engagement, perceived agency, and emotional response, which remain open to future empirical study. Video illustrations: https://www.youtube.com/playlist?list=PLMu36WzSQKiVeBnrUdwUAoUhqLqGX3bw and implementation: https://github.com/KairosHive/retina-cinema.
Create a lesson
Related papers
Rethinking Utility in Differentially Private Visualization: A Channel-Centric Perspective
Jing Yang, Sarayu Pacca, Zhaocong Yang et al.
Presenting Your Figures: Data-informed Animated Transitions Across Scientific Figure Panels
Lu Ying, Can Liu, Yuxiao Yang et al.
Ground Truth Bias in AI-Assisted Medical Annotation: A Crossover Study Using an Independent Radiologist Reference Standard
Márton Baltay, Tamás Ilcsik, Márton Borbély
Embodied Human-Data Interaction
Niklas Elmqvist
From Reliance to Overreliance: Taxonomizing and Detecting Relational Risks in AI Companionship
Viet Cuong Nguyen, Fiona Li, Chang Wan et al.
GenAI-DBT: Evaluating a DBT-Informed Generative AI Platform for Mindfulness Skills Training: A Pilot Randomized Study
Jingchen Ye, Yujia Chen, Leyang Han et al.