If you’ve ever seen a piece of wooden furniture that you wanted to recreate , you’re in luck.
at the University of Washington in Seattle and his colleagues have created an algorithm that turns photos of wooden objects into a 3D model that is detailed enough for a skilled carpenter to replicate.
A common problem with algorithms designed to reverse engineer a 3D object like a piece of furniture is that if there isn’t enough data, the software will produce a low-detail model that is unsuitable for physical construction. The team got around this by considering the geometric limitations of flat sheets of wood and the ways wooden parts can fit together.
Advertisement
“It doesn’t really require that you observe the object completely because we make these assumptions about how objects are fabricated, we don’t need to take pictures of every single surface which is something you would need for a traditional 3D reconstruction algorithm to get complete shapes,” says Noeckel.
To test the algorithm, the team took photos of wooden items, such as a bookcase, using a smartphone. After less than 10 minutes of processing the images on a computer, the algorithm produced 3D plans showing the configuration of the item, including its component parts and how to fit them together. A future version could run directly on the phone, says Noeckel.
“The final product would be an app you could have on your phone and take a bunch of pictures of furniture, run an algorithm, and you would pretty much 100 per cent of the time get the correct blueprint for the object in the form of a nice 3D model that also includes instructions for how to assemble it,” says Noeckel. “It is a scenario where the user doesn’t have to do a lot of work.”
Reference:
