Metraipolis › archive › dc_579969c03421
ShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality — arXiv:2610.19998
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19998
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:46:47.728Z
- SHA-256 of the archived text
93be72325df1d02ab31bc7a92201576e63f46d7c7d6173628ecdc089ca7394b4- Stable URL of this page
https://metraipolis.com/documento/dc_579969c03421
How to cite
ShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality — arXiv:2610.19998 — arXiv (en), https://arxiv.org/abs/2610.19998 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_579969c03421 (Metraipolis archive dc_579969c03421, sha256 93be72325df1d02ab31bc7a92201576e63f46d7c7d6173628ecdc089ca7394b4)
BibTeX
@misc{dc579969c03421,
title = {ShadAR: Real-time Prompting On-demand Visual Augmentation in Augmented Reality — arXiv:2610.19998},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19998},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_579969c03421; sha256 93be72325df1d02ab31bc7a92201576e63f46d7c7d6173628ecdc089ca7394b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19998. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Augmented Reality can reshape our visual perception (e.g., simulating color blindness) yet such effects are typically pre-programmed by experts, making visual augmentation static and inflexible. We introduce ShadAR, an AR system that allows users to describe expected visual augmentations (e.g., "Blur all people") for changing their vision in real time. ShadAR can graphically manipulate AR passthrough in real time via shader injection. When receiving a user's prompt, ShadAR uses LLMs (GPT5.2) to interpret the user's intent, analyzes the user's view with object detection (YOLOv26), generates a pixel shader, and applies it to the targeted region on AR passthrough. To understand usage patterns, we invited 21 HCI researchers to use ShadAR, identifying four application domains (design, health, productivity, and social interaction) and two prompt-framing patterns: procedural prompts specifying what to modify and how ("Highlight the book."), and end-goal prompts conveying desired mental or behavioral states ("Make me laugh."). Such end-goal prompts suggest a future in which users specify outcomes (e.g., "Make me not miss my flight") while the system determines how to realize them, though often with inherently indeterminate results. We discuss design opportunities for ShadAR and ethical concerns.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.19998 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T21:33:59.692Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).