Scientists develop new software that can crate 3D models from 2D photographs
Scientists including one of Indian origin have developed new artificial intelligence (AI) software called SurfNet that can create three dimensional (3D) models from 2D photographs.
When fully developed SurfNet could have significant applications in the fields of 3D searches on the internet researchers. In an advance version it can allow future robots to navigate in the real world.
SurfNet software using hundreds of thousands of 2D shapes of objects can reconstruct it model in 3D. It utilizes machine learning to analyze 2D shapes and convert them into projected 3D forms. In addition to transforming 2D shapes, the technology can also merge two shapes into one another. The technology becomes more refined over time as the AI learns more about the shapes.
Future potential application: It can be used in robotics, object recognition and even self-driving cars. SurfNet will give them ability to understand the 3D environment around them using standard 2D cameras. It can also be used to create 3D content for virtual reality (VR) and augmented reality (AR) by simply using standard 2D photos.
Artificial intelligence is the branch of computer science concerned with making computers behave like humans. In contrast to normal hardware and software, AI enables a machine to perceive and respond to its changing environment.