NVIDIA researchers created a machine learning called DIB-R that can turn 2D images into 3D models. Artificial Intelligence will be able to predict how a 2D image would look like in three dimensions. With the help of lighting, texture, depth, and all sorts of different viewpoints, the 3D model can be made. It would be useful in robotics.
The invention will be presented at the annual conference on NeurIPS in Vancouver. As per NVIDIA’s website, “For an autonomous robot to interact safely and efficiently with its environment, it must be able to sense and understand its surroundings. DIB-R could potentially improve those depth perception capabilities.”