technophyl

prostheticknowledge:

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Research from @Nvidia has taken neural network image synthesis to much higher visual definition than has previously been achieved:

The video below has no audio and example results starts approximately 38 seconds into it:

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively, starting from low-resolution images, and add new layers that deal with higher resolution details as the training progresses. This greatly stabilizes the training and allows us to produce images of unprecedented quality, e.g., CelebA images at 1024² resolution. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several small implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution we construct a higher quality version of the CelebA dataset that allows meaningful exploration up to the resolution of 1024² pixels. 

More Here