The Joy of Neural Painting
This work addresses training inefficiencies for AI art generation, but it is incremental as it builds on existing GAN frameworks.
The authors tackled the problem of slow and difficult training of GAN-based neural painting models by applying transfer learning, reducing training time from days to hours while maintaining the same visual quality in generated paintings.
Neural Painters is a class of models that follows a GAN framework to generate brushstrokes, which are then composed to create paintings. GANs are great generative models for AI Art but they are known to be notoriously difficult to train. To overcome GAN's limitations and to speed up the Neural Painter training, we applied Transfer Learning to the process reducing it from days to only hours, while achieving the same level of visual aesthetics in the final paintings generated. We report our approach and results in this work.