NVIDIA researchers have developed an AI-based system that can look at an image of a sunny road, and imagine it in extreme detail, what it would look like if it were raining, nighttime, or even a snowy day. This software utilizes a new approach in AI that enables computers to learn without human intervention, or in other words, generative adversarial networks (GANs), which are neural networks that work together to learn the properties of a data set. Continue reading to see the day to night transition video (left is reality, and right is AI).
“In a GAN, one neural network tries to produce synthetic data while another tries to tell if an example comes from the real data set or not. Feedback from the second network helps improve the performance of the first. The trick performed by the Nvidia team is to use two GANs trained on different but similar data, and to use similarities, or overlap, between the two trained models to dream up new imagery,” according to MIT engineers.