arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.17481cs.HC
收藏

ShadAR: 基于大语言模型的着色器生成以在增强现实中转变视觉感知

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

TU Darmstadt(达姆施塔特工业大学)

Yanni Mei, Samuel Wendt, Florian Mueller, Jan Gugenheimer

AI总结:

ShadAR利用大语言模型生成着色器,实现增强现实中的视觉感知实时转变,提升包容性和创造性。

摘要:

增强现实(AR)可以模拟各种视觉感知,例如色盲者如何看待世界。然而,这些模拟需要开发人员预先定义每种视觉效果,限制了灵活性。我们提出了ShadAR,一种AR应用,通过使用大语言模型(LLMs)生成着色器,实现视觉感知的实时转变。ShadAR允许用户通过自然语言表达其视觉意图,该意图由LLM解释并生成相应的着色器代码。然后,该着色器被实时编译以修改AR头戴设备的视口。我们展示了我们的LLM驱动的着色器生成流水线,并证明了其能够为包容性和创造性转变视觉感知的能力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑