AltCanvas: A Tile-Based Image Editor with Generative AI for Blind or Visually Impaired People

TL;DR

AltCanvas is an accessible, tile-based image editing system that combines generative AI with constructive controls, enabling visually impaired users to create and edit visual scenes with speech feedback.

Contribution

It introduces a novel tile-based interface integrating generative AI with constructive editing for visually impaired users, enhancing control and expressiveness in image creation.

Findings

Participants successfully created illustrations using AltCanvas.

The system improved accessibility and control in image editing for visually impaired users.

User feedback was positive regarding usability and functionality.

Abstract

People with visual impairments often struggle to create content that relies heavily on visual elements, particularly when conveying spatial and structural information. Existing accessible drawing tools, which construct images line by line, are suitable for simple tasks like math but not for more expressive artwork. On the other hand, emerging generative AI-based text-to-image tools can produce expressive illustrations from descriptions in natural language, but they lack precise control over image composition and properties. To address this gap, our work integrates generative AI with a constructive approach that provides users with enhanced control and editing capabilities. Our system, AltCanvas, features a tile-based interface enabling users to construct visual scenes incrementally, with each tile representing an object within the scene. Users can add, edit, move, and arrange objects while receiving speech and audio feedback. Once completed, the scene can be rendered as a color illustration or as a vector for tactile graphic generation. Involving 14 blind or low-vision users in design and evaluation, we found that participants effectively used the AltCanvas workflow to create illustrations.