@inproceedings{Mei2026Shadar,
title = {ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality},
author = {Yanni Mei (TU Darmstadt), Samuel Wendt (TU Darmstadt), Jonas Wombacher (TU Darmstadt), Florian Müller (TU Darmstadt), Jan Gugenheimer (TU Darmstadt)},
url = {https://www.informatik.tu-darmstadt.de/hci/hci_tuda/index.en.jsp, website},
doi = {10.1145/3772363.3799378},
year = {2026},
date = {2026-04-13},
urldate = {2026-04-13},
abstract = {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.},
keywords = {Interactive Demos},
pubstate = {published},
tppubtype = {inproceedings}
}