Autodesk Launches Project Bernini to Show New Way to Generate 3D Assets
Autodesk tech preview shows how you can generate 3D objects from text, image, voxel, and point-cloud input
May 28, 2024
In early May, Autodesk launches Project Bernini, an AI-powered 3D asset generator. Targeting the design and make market, “the first experimental Bernini model quickly generates functional 3D shapes from a variety of inputs including 2D images, text, voxels, and point clouds,” according to the company's announcement.
Project Bernini mirrors how AI-based image generators like Midjourney or Microsoft Image Creator works, with one key difference: It generates 3D objects. The project raises the possibility that users may further train the generative algorithm with proprietary data to improve the output results. It may also usher in easier, faster ways to create 3D content—the main purpose of many Autodesk software titles.
“We’re intently focused on generating functional 3D structures because the articles built or manufactured from the outputs of these models must work in the real world, serving the purpose that the designer has in mind,” Autodesk says. In demonstrating how Bernini creates a typical water pitcher, the company says, “Bernini model generates shape and texture separately and does not confuse or meld those variables. So, water pitchers generated by our model are hollow in the middle and could actually hold water, as any real-world pitcher would need to do.”
The technology is developed by Autodesk Research, the branch responsible for exploring new possibilities and usage paradigms. As part of Autodesk Research, the Autodesk AI Lab “trained the Bernini model on ten million diverse 3D shapes—a composite dataset made up of publicly available data, a mixture of CAD objects and organic shapes,” the company explains. The program exports objects in OBJ format.
Autodesk AI is expected to reshape the UI of the company's design and simulation software titles. At SIGGRAPH 2023, Autodesk demonstrated an AI-powered application to generative 2D automotive design. The app uses Stable Diffusion and can accepting both text prompts and images as input to generate professional-looking 2D automotive sketches, complete with backgrounds. Last year, NVIDIA also added a similar feature in its immersive environment Omniverse with the AI Room Generator Extension.
Currently Project Bernini is a proof of concept still in incubation, not available to outside users. The company has not given details on when public beta might be released.
More Autodesk Coverage
For More Info
Subscribe to our FREE magazine,
FREE email newsletters or both!About the Author
Kenneth WongKenneth Wong is Digital Engineering’s resident blogger and senior editor. Email him at [email protected] or share your thoughts on this article at digitaleng.news/facebook.
Follow DE