A new innovative tool, A11yShape, has the potential to revolutionize 3D modeling for visually impaired people. Developed by a research team led by Liang He, an assistant professor of computer science at the University of Texas at Dallas, A11yShape features three interactive panels: a code editor panel, an AI assistance panel, and a model panel. Our unique solution combines code with AI-based technical descriptions and the model structure. Today, blind programmers can freely experiment with how tweaks in their coding affect their designs on their own.
The project originated from a conversation he had with a Scripps classmate. This classmate, who experiences low vision, was in the midst of a course of 3D modeling. This powerful dialogue encouraged us to produce a new tool. We hope to use this knowledge and technology to help visually impaired people participate more fully in the design process.
Functionality of A11yShape
A11yShape wraps these three important concepts up in a nice package that work in concert with each other. The dedicated code editor panel offers full programming support, enabling users to write and modify their code more efficiently. The AI-powered help panel provides ongoing, in-context suggestions that improve the user’s comprehension of the coding process. At the same time, the model panel shows the hierarchy and real-time rendering of the final resulting 3D model.
The synchronization among these panels is crucial. Once a user hovers over and selects a line of code or a model component, A11yShape kicks in. It shows how the appropriate elements are aligned across all three panels. This purposeful addition makes a tremendous difference to understanding. By dynamically changing descriptions based on user selection, it lets users drill down deeper to explore complicated interactions that are built-in to the modeling process.
“I want to design something useful and practical for the group,” – Liang He
User Engagement and Feedback
To make sure the tool was working as desired, the research team brought in four participants with different levels of visual impairments and programming experience. These participants provided valuable insights during testing. Their thoughtful feedback helped us realize that A11yShape really does contribute a positive approach to improving accessibility in 3D modeling.
Participants said the AI-generated descriptions were consistently scoring at a 4 out of 5 or higher. Their average scores went from ~ 4.1 to 5 for geometric correctness, clarity, no hallucinations. This reliability and confidence leads us to believe that A11yShape’s AI features could be used in an everyday manner.
“On a 1–5 scale, the descriptions earned average scores between about 4.1 and 5 for geometric accuracy, clarity, and avoiding hallucinations, suggesting the AI is reliable enough for everyday use.” – Source not explicitly mentioned
One participant, who had never modeled before, expressed the significance of A11yShape:
“It provided [the blind and low-vision community] with a new perspective on 3D modeling, demonstrating that we can indeed create relatively simple structures.”
The Broader Impact of A11yShape
A11yShape is a great, technical solution. Additionally, it encourages novel forms of creativity and expression among the blind and visually impaired. As an advocate for accessibility in technology, artist Stephanie Ludi emphasized the personal aspect of self-expression with tools such as A11yShape.
“People like being able to express themselves in creative ways… using technology such as 3D printing to make things for utility or entertainment,” – Stephanie Ludi
This project is a huge jump in the right direction to make the world of technology more accessible and inclusive. A11yShape provides the tools to help visually impaired users explore 3D models independently and intuitively. This breakthrough breaks decades-old barriers that have limited access to design tools.
