Disentangling Style and Content in Anime Illustrations
This addresses the challenge of generating stylized content while preserving semantics for anime art creation and style transfer, though it is incremental as it builds on existing disentanglement methods.
The paper tackles the problem of disentangling style and content in anime illustrations, proposing a Generative Adversarial Disentanglement Network that can generate high-fidelity anime portraits with fixed content and varied styles from over a thousand artists, showing superior output to state-of-the-art methods.
Existing methods for AI-generated artworks still struggle with generating high-quality stylized content, where high-level semantics are preserved, or separating fine-grained styles from various artists. We propose a novel Generative Adversarial Disentanglement Network which can disentangle two complementary factors of variations when only one of them is labelled in general, and fully decompose complex anime illustrations into style and content in particular. Training such model is challenging, since given a style, various content data may exist but not the other way round. Our approach is divided into two stages, one that encodes an input image into a style independent content, and one based on a dual-conditional generator. We demonstrate the ability to generate high-fidelity anime portraits with a fixed content and a large variety of styles from over a thousand artists, and vice versa, using a single end-to-end network and with applications in style transfer. We show this unique capability as well as superior output to the current state-of-the-art.