Scientists, including one of Indian origin, have developed a new artificial intelligence software that can create 3D models from two dimensional photographs, an advance that could allow future robots to navigate in the real world.
When fully developed, the method called SurfNet could have significant applications in the fields of 3D searches on the internet researchers said.
“The “magical” capability of AI deep learning is that it is able to learn abstractly,” said Karthik Ramani, professor at Purdue University in the US.
“If you show it hundreds of thousands of shapes of something such as a car, if you then show it a 2D image of a car, it can reconstruct that model in 3D,” Ramani said.
“It can even take two 2D images and create a 3D shape between the two, which we call hallucination,” he added.
Perhaps most exciting, however, is that the technique could be used to create 3D content for virtual reality and augmented reality by simply using standard 2D photos.
“You can imagine a movie camera that is taking pictures in 2D, but in the virtual reality world everything is appearing magically in 3D,” Ramani said.
“Inch-by-inch we are going there, and in the next five years something like this is going to happen,” he said.
One significant outcome of the research would be for robotics, object recognition and even self-driving cars in the future.
They would only need to be fitted with standard 2D cameras, yet still have the ability to understand the 3D environment around them.