Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
This work addresses the need for efficient and adaptable stylization tools for digital AI artists, representing an incremental improvement over existing methods.
The paper tackles the problem of image stylization by proposing a method that combines parametric and non-parametric approaches to enable fast and flexible stylization from small datasets, resulting in a model that reduces computational requirements while maintaining quality.
Parametric generative deep models are state-of-the-art for photo and non-photo realistic image stylization. However, learning complicated image representations requires compute-intense models parametrized by a huge number of weights, which in turn requires large datasets to make learning successful. Non-parametric exemplar-based generation is a technique that works well to reproduce style from small datasets, but is also compute-intensive. These aspects are a drawback for the practice of digital AI artists: typically one wants to use a small set of stylization images, and needs a fast flexible model in order to experiment with it. With this motivation, our work has these contributions: (i) a novel stylization method called Fully Adversarial Mosaics (FAMOS) that combines the strengths of both parametric and non-parametric approaches; (ii) multiple ablations and image examples that analyze the method and show its capabilities; (iii) source code that will empower artists and machine learning researchers to use and modify FAMOS.