A team of researchers from MIT CSAIL and QCRI have developed a neural network that can look at an image of a pizza, determine the type and distribution of ingredients, and figure out the correct order to layer the pizza before cooking.
They developed the AI with the ability to visualize what a pizza ought to look like based on whether ingredients have been added or removed. Show it a picture of a pizza with everything on it, and if you then ask it to remove the onions and green peppers it can generate a modified image.
"Though we have evaluated our model only in the context of pizza, we believe that a similar approach is promising for other types of foods that are naturally layered such as burgers, sandwiches, and salads," the team wrote in the new paper. "Beyond food, it will be interesting to see how our model performs on domains such as digital fashion shopping assistants, where a key operation is the virtual combination of different layers of clothes."