This AI-driven tool makes customizing 3D-printable models easier
MIT researchers have developed a generative-AI-driven tool that allows users to add custom design elements to 3D models without affecting their functionality
3D-printed objects are becoming more mainstream now. We are seeing their applications in everything from food (be it 3D-printed meat) to the automobile industry (Elon Musk’s Tesla is reportedly experimenting with 3D printing to make its car’s bodies).
Researchers at the Massachusetts Institute of Technology (MIT) have now developed a generative-AI-driven tool that enables the user to add custom design elements to 3D models without compromising the functionality of the fabricated objects.
3D printers have become cheaper and more accessible now. According to an MIT news release, there’s also a fast-growing community of novice makers that design their own objects using this method. To do this, many of these amateur designers access free, open-source repositories of user-generated 3D models, which they download and fabricate on a 3D printer. But adding custom design elements to these models can be challenging, the news release explains. This requires the use of expensive computer-aided design software. There’s also the possibility of customization affecting the functionality of the final 3D printed object, which requires further expertise in the field.
With Style2Fab, the name of the AI-driven tool, amateur 3D printing desingers can personalize 3D models of objects using only natural language prompts to describe their desired design. The user could then fabricate the objects with a 3D printer, the MIT news release adds. “For someone with less experience, the essential problem they faced has been: Now that they have downloaded a model, as soon as they want to make any changes to it, they are at a loss and don’t know what to do. Style2Fab would make it very easy to stylize and print a 3D model, but also experiment and learn while doing it,” Faraz Faruqi, a computer science graduate student and lead author of a paper introducing Style2Fab, says in the MIT news release.
This tool – which is driven by deep-learning algorithms that automatically partition the model into aesthetic and functional segments -- could not only help amateur designers but also make 3D printing more accessible. Style2Fab, for instance, could also be utilized in the emerging area of medical making, the news release explains. As an example: with Style2Fab, a user could customize the appearance of a thumb splint so it blends in with his or her clothing without altering the functionality of the medical device. Providing a user-friendly tool for the growing area of DIY assistive technology was a major motivation for this work, Faruqi says in the news release.
Faruqi wrote the paper with his advisor, co-senior author Stefanie Mueller, an associate professor in the MIT departments of Electrical Engineering and Computer Science and Mechanical Engineering, and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL) who leads the HCI Engineering Group; co-senior author Megan Hofmann, assistant professor at the Khoury College of Computer Sciences at Northeastern University; as well as other members and former members of the group. The research will be presented at the ACM Symposium on User Interface Software and Technology in San Francisco, California next month.
Going forward, the researchers want to extend Style2Fab so the system offers more control over physical properties as well as geometry. They also intend to enhance Style2Fab so a user could generate their own custom 3D models from scratch within the system. The researchers are also collaborating with Google on a follow-up project, the MIT news release explains.
(With inputs from MIT News)
Catch all the Business News, Market News, Breaking News Events and Latest News Updates on Live Mint. Download The Mint News App to get Daily Market Updates.
MoreLess
First Published:18 Sep 2023, 01:00 PM IST
- Top Gainers
- Top Losers
- 52 Week High