Generative AI for Accessible and Inclusive Extended Reality

TL;DR

This paper explores how AI-generated content can make extended reality more accessible and inclusive by reducing technical barriers and enhancing content creation and interaction.

Contribution

It analyzes benefits and challenges of using AI for creating accessible virtual environments, highlighting new opportunities and issues in the field.

Findings

AIGC reduces need for 3D modeling expertise

Multimodal input enhances virtual environment creation

Foundation models introduce specific accessibility challenges

Abstract

Artificial Intelligence-Generated Content (AIGC) has the potential to transform how people build and interact with virtual environments. Within this paper, we discuss potential benefits but also challenges that AIGC has for the creation of inclusive and accessible virtual environments. Specifically, we touch upon the decreased need for 3D modeling expertise, benefits of symbolic-only as well as multimodal input, 3D content editing, and 3D model accessibility as well as foundation model-specific challenges.