We examined the use of modern Generative Adversarial Nets to generate novel images of oil paintings using the Painter By Numbers dataset. We implemented Spectral Normalization GAN (SN-GAN) and Spectral Normalization GAN with Gradient Penalty, and compared their outputs to a Deep Convolutional GAN. Visually, and quantitatively according to the Sliced Wasserstein Distance metric, we determined that the SN-GAN produced paintings that were most comparable to our training dataset. We then performed a series of experiments to add supervised conditioning to SN-GAN, the culmination of which is what we believe to be a novel architecture that can generate face paintings with user-specified characteristics.
@article{arxiv.1903.06259,
title = {Conditional GANs For Painting Generation},
author = {Adeel Mufti and Biagio Antonelli and Julius Monello},
journal= {arXiv preprint arXiv:1903.06259},
year = {2019}
}