In the area of 3D modeling, a new tool called A11yShape is taking great leaps forward. It’s purpose-built for helping users who are blind or low vision. This groundbreaking application features a web interface that includes three synchronized panels: a code editor, an AI assistance panel, and a model panel. A11yShape’s goal is to arm blind and low-vision people with the tools, resources, and encouragement to participate in the world of 3D modeling in a productive way.
A11yShape started when developer Liang He was talking to a classmate with low vision. They were both new to 3D modeling at the time. The project is ultimately going to better equip users, because it’ll give them a more intuitive way to interpret their work. Through the use of advanced AI technology, A11yShape provides contextual feedback, guiding users through complicated modeling tasks with ease.
Features of A11yShape
A11yShape is made up of three separate panels that interact with each other in real-time. The code editor is where users get to write and test their own code. At the same time, the AI assistance panel provides instant feedback to improve the coding experience. The model panel illustrates the nested structure of the model. It looks at the design, allowing users to see the effect of their changes live.
The most important feature of A11yShape is its ability to highlight matching components in all three panels. Whenever a user hovers over a line of code or a certain part of the model, A11yShape instantaneously changes descriptions in real time. This instant syncing of changes helps users know what they’re changing. It trains them in understanding how changes to the code they write affect outcomes in design.
The AI assistance panel has been nothing short of astounding. It regularly scores above 4.1 and as high as 5 across the board for geometric fidelity, clarity, and reducing of manufacturing hallucinations. This gives users the confidence that the AI is trustworthy enough to be used in day-to-day scenarios, which greatly improves the user experience.
“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.” – Research team
User-Centric Design Process
To further refine A11yShape, the research team engaged four participants with varying degrees of visual impairments and backgrounds in programming. Having a diverse group of individuals using the tool was imperative to understanding its usability, effectiveness and overall value. Liang He was very passionate about producing something that would be practical and effect the visually impaired community.
“I want to design something useful and practical for the group,” – Liang He
User feedback showed that creativity plays a huge role in 3D modeling. Stephanie Ludi noted that technology such as 3D printing allows individuals to express themselves in innovative ways, whether for utility or entertainment. Their team is passionate about how A11yShape can help close the existing chasms of access to creative tools that require visual perception, especially for visual impaired disabilities.
“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
Future Developments
Looking ahead, the team behind A11yShape pictures adding many new tools to improve its usefulness and broaden its applications. Future versions will use tactile displays and real-time 3D printing capabilities, greatly increasing accessibility from what is already available for use by individuals with visual impairments. On top of that, they want to use AI to create shorter audio descriptions, enabling an even more seamless experience for their users.
Liang He reminded people that designs need to be pragmatic. He has little interest in producing theoretical constructs which don’t have functional solutions. Rather, his goal is to create solutions that address actual needs for people who are blind or have other visual impairments.
“Not just something I created from my imagination and applied to the group,” – Liang He