Yanni Mei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yanni Mei has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jan Gugenheimer
TU Darmstadt, Darmstadt, Germany
4 shared publications - Florian Müller
TU Darmstadt
3 shared publications - Jonas Wombacher
TU Darmstadt, Darmstadt, Germany
3 shared publications - Samuel Wendt
TU Darmstadt, Darmstadt, Germany
3 shared publications - Veronika Krauß
Responsible System Design, Ansbach University, Ansbach, Germany
1 shared publication - Wen-Jie Tseng
LTCI, INFRES, Telecom Paris, Institut Polytechnique de Paris, France
1 shared publication
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Toward Experience Augmentation in Everyday Augmented Reality
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessToward Experience Augmentation in Everyday Augmented Reality
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
ShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Meme, Myself and AR: Exploring Memes Sharing in Face-to-face Conversation using Augmented Reality
Internet memes are central to online communication, yet their visual humor is often lost in face-to-face (F2F) conversations. Augmented reality (AR) offers new ways to bring memes into F2F interactions, but it is unclear how memes can be integrated into F2F conversations using AR, and how they impact conversational dynamics. We surveyed meme users (N=29) to understand motivations and challenges in visualising memes in F2F conversations. With these insights, we developed an AR meme-sharing prototype and invited 12 pairs of friends to design AR visualizations for their memes and use them in conversations. Our analysis reveals two AR-unique visualizations: merging memes with one’s body (The-Meme-On-Me) and situating oneself in meme environment (Me-In-The-Meme). We observed two integration patterns: using speech as setup before a meme punchline, and showing memes simultaneously with speech to amplify humor. We report users’ reactions toward AR memes, showing how it enables playful social interaction.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessMeme, Myself and AR: Exploring Memes Sharing in Face-to-face Conversation using Augmented Reality
Internet memes are central to online communication, yet their visual humor is often lost in face-to-face (F2F) conversations. Augmented reality (AR) offers new ways to bring memes into F2F interactions, but it is unclear how memes can be integrated into F2F conversations using AR, and how they impact conversational dynamics. We surveyed meme users (N=29) to understand motivations and challenges in visualising memes in F2F conversations. With these insights, we developed an AR meme-sharing prototype and invited 12 pairs of friends to design AR visualizations for their memes and use them in conversations. Our analysis reveals two AR-unique visualizations: merging memes with one’s body (The-Meme-On-Me) and situating oneself in meme environment (Me-In-The-Meme). We observed two integration patterns: using speech as setup before a meme punchline, and showing memes simultaneously with speech to amplify humor. We report users’ reactions toward AR memes, showing how it enables playful social interaction.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality
Augmented Reality (AR) can visually transform a user’s world by rendering virtual content on top of reality. However, developing such AR apps and visualizations remains a complex process that requires an understanding of computer vision and programming skills. We present ShadAR, an AR prototyping pipeline that enables real-time creation of small AR visualizations and applications using large language models (LLMs) and object detection. ShadAR allows users to express their visual intent (e.g., pixelate every person around me) via natural language, which is interpreted by an LLM to generate corresponding shader code. This shader is then compiled in real-time and applied to the passthrough video stream.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality
Augmented Reality (AR) can visually transform a user’s world by rendering virtual content on top of reality. However, developing such AR apps and visualizations remains a complex process that requires an understanding of computer vision and programming skills. We present ShadAR, an AR prototyping pipeline that enables real-time creation of small AR visualizations and applications using large language models (LLMs) and object detection. ShadAR allows users to express their visual intent (e.g., pixelate every person around me) via natural language, which is interpreted by an LLM to generate corresponding shader code. This shader is then compiled in real-time and applied to the passthrough video stream.
- 2 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (5) , 4154-4164
Embodied Spatial Simulation: Enabling Embodied Interaction with Human Motion Simulation in Extended Reality
Human Motion Simulation (HMS) predicts and visualizes how virtual agents move and behave in various scenarios, aiding decision-making. However, it does not communicate the experience behind agents' behavior. To address this, we present Embodied Spatial Simulation (ESS), a concept combining augmented reality(AR) and HMS to support in-situ decision-making. It enables an XRuser to create “what-if” scenarios, simulate virtual agents' behavior in situ, and experience the scenarios from their perspectives through embodiment. To demonstrate ESS, we developed a proof-of-concept prototype featuring two scenarios (e.g., fire evacuation planning). From expert walkthroughs (N = 4) and a survey (N = 38) with different professions, we found that incorporating embodiment into simulations can change users' intentions to use simulation outcomes. Rather than directly obtaining solutions from the results, users showed more interest in understanding the experience behind simulated behavior and using this insight to shape decisions. We discuss the potential of ESS to support future human-centered design practices.
- 2 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (5) , 4154-4164
Embodied Spatial Simulation: Enabling Embodied Interaction with Human Motion Simulation in Extended Reality
Human Motion Simulation (HMS) predicts and visualizes how virtual agents move and behave in various scenarios, aiding decision-making. However, it does not communicate the experience behind agents' behavior. To address this, we present Embodied Spatial Simulation (ESS), a concept combining augmented reality(AR) and HMS to support in-situ decision-making. It enables an XRuser to create “what-if” scenarios, simulate virtual agents' behavior in situ, and experience the scenarios from their perspectives through embodiment. To demonstrate ESS, we developed a proof-of-concept prototype featuring two scenarios (e.g., fire evacuation planning). From expert walkthroughs (N = 4) and a survey (N = 38) with different professions, we found that incorporating embodiment into simulations can change users' intentions to use simulation outcomes. Rather than directly obtaining solutions from the results, users showed more interest in understanding the experience behind simulated behavior and using this insight to shape decisions. We discuss the potential of ESS to support future human-centered design practices.