Generative image synthesis for training deep learning machines

摘要

A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.