Research

Paper

AI LLM February 19, 2026

ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality

Authors

Yanni Mei, Samuel Wendt, Florian Mueller, Jan Gugenheimer

Abstract

Augmented Reality (AR) can simulate various visual perceptions, such as how individuals with colorblindness see the world. However, these simulations require developers to predefine each visual effect, limiting flexibility. We present ShadAR, an AR application enabling real-time transformation of visual perception through shader generation using large language models (LLMs). ShadAR allows users to express their visual intent via natural language, which is interpreted by an LLM to generate corresponding shader code. This shader is then compiled real-time to modify the AR headset viewport. We present our LLM-driven shader generation pipeline and demonstrate its ability to transform visual perception for inclusiveness and creativity.

Metadata

arXiv ID: 2602.17481
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17481v1</id>\n    <title>ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality</title>\n    <updated>2026-02-19T15:50:32Z</updated>\n    <link href='https://arxiv.org/abs/2602.17481v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17481v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Augmented Reality (AR) can simulate various visual perceptions, such as how individuals with colorblindness see the world. However, these simulations require developers to predefine each visual effect, limiting flexibility. We present ShadAR, an AR application enabling real-time transformation of visual perception through shader generation using large language models (LLMs). ShadAR allows users to express their visual intent via natural language, which is interpreted by an LLM to generate corresponding shader code. This shader is then compiled real-time to modify the AR headset viewport. We present our LLM-driven shader generation pipeline and demonstrate its ability to transform visual perception for inclusiveness and creativity.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-02-19T15:50:32Z</published>\n    <arxiv:primary_category term='cs.HC'/>\n    <arxiv:journal_ref>2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), Daejeon, Korea, Republic of, 2025, pp. 959-960</arxiv:journal_ref>\n    <author>\n      <name>Yanni Mei</name>\n    </author>\n    <author>\n      <name>Samuel Wendt</name>\n    </author>\n    <author>\n      <name>Florian Mueller</name>\n    </author>\n    <author>\n      <name>Jan Gugenheimer</name>\n    </author>\n    <arxiv:doi>10.1109/ISMAR-Adjunct68609.2025.00267</arxiv:doi>\n    <link href='https://doi.org/10.1109/ISMAR-Adjunct68609.2025.00267' rel='related' title='doi'/>\n  </entry>"
}