A collection of GAN. GAN is a new generator architecture for generative adversarial networks that enables unsupervised separation of high-level attributes and stochastic variation in generated images. This generator improves the state-of-the-art in distribution quality metrics and disentangles latent factors of variation. The article also introduces two new automated methods to quantify interpolation quality and disentanglement, and a new dataset of human faces.

Can you tell if an image was generated by a human or a machine ? : https://thisimagedoesnotexist.com/

A database project that aggregates tools and resources for artists, engineers, curators, and researchers interested in incorporating machine learning (ML) and other forms of artificial intelligence (AI) into their practice. The database contains resources from partners and networks and covers a broad spectrum of possibilities presented by the current advances in ML, enabling users to generate images, create interactive artworks, draft texts, or recognize objects. While most of the tools require coding skills, the database includes entries tagged as courses and encourages beginners to turn to RunwayML. The article notes that the database is not comprehensive and is a growing collection of research commissioned and collected by the Creative AI Lab, with new entries added regularly.