Autodesk has unveiled its first experimental generative AI model to generate accurate AI 3D shapes from a variety of inputs
Project Bernini’s generative AI can create 3D shapes from inputs including single 2D images, multiple images showing different views of an object, point clouds, voxels and text.
The Autodesk AI Lab within Autodesk Research trained the Bernini model on 10m diverse 3D shapes – a composite dataset made up of publicly available data, a mixture of CAD objects and organic shapes. Research that contributed toward this work was published earlier this year by the AI Lab in collaboration with the Chinese University of Hong Kong.
The first Bernini model is acutely geared toward professional geometric workflows and can generate multiple functional variations of a 3D shape from a given input.
Autodesk said it is working to create generative models that could be used for different use cases across architecture, engineering, product design, entertainment, and more.
3D models for the real world
Project Bernini is 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 cited a water pitcher as an example. While many 3D generative AI models can produce shapes that look like a pitcher, with textures that improve their superficial appearance in a specific lighting environment.
The Bernini model, however, generates shape and texture separately, and does not confuse or meld those variables. So a water pitcher generated by the model is hollow in the middle and could actually hold water, as any real world pitcher would need to do.
In addition, Project Bernini’s generative AI approach produces several variants, giving designers a choice and contributing to the creative workflow.
‘Inspiring a new generation of buildings and architects’
Autodesk said that at this stage, Project Bernini remains strictly experimental.
However, as the technology is refined, it is actively engaging potential partners to further study and improve the performance of generative AI models.
“While Project Bernini is exciting and at the leading edge of generative AI, its models will become increasingly useful and compelling when trained on larger, higher-quality professional datasets. The Bernini model is specifically structured to offer efficient training and fine-tuning to easily allow this,” the company said in a statement.
“If trained on buildings, the models could generate geometrically rigorous creative designs and inspire a new generation of buildings and architects. If trained on video game character models or fantasy environments, they could produce fascinating new creatures or virtual worlds. If trained on car designs, they could assist in imagining an innovative new series of vehicles.”
According to Autodesk’s 2024 State of Design & Make report, 78% of business leaders believe AI will enhance their industry and 79% agree that AI will make their industry more creative.
