ShadAR: LLM-driven shader generation to transform visual perception in Augmented Reality
Authors:
- 8 October 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 959-960
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’s viewport. We present our LLM-driven shader generation pipeline and demonstrate its ability to transform visual perception for inclusiveness and creativity.Keywords
All Related Versions
Funding Information
- EWE
This publication has 7 references indexed in Scilit:
- LLM Integration in Extended Reality: A Comprehensive Review of Current Trends, Challenges, and Future Perspectives2025
- A Design Space for Vision Augmentations and Augmented Human Perception using Digital Eyewear2024
- LLMR: Real-time Prompting of Interactive Worlds using Large Language Models2024
- Seeing our Blind Spots: Smart Glasses-based Simulation to Increase Design Students’ Awareness of Visual Impairment2022
- CatARact: Simulating Cataracts in Augmented Reality2020
- Immersive Simulation of Visual Impairments Using a Wearable See-through Display2015
- Augmented Reality Art2014