Disentangling Style and Content in Anime Illustrations
arXiv:1905.10742
Abstract
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.
References in corpus (8)
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Deep Convolutional Inverse Graphics Network
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Disentangling factors of variation in deep representations using adversarial training
- Cold Case: The Lost MNIST Digits
- Learning Ordered Representations with Nested Dropout
- Can Computers Create Art?
- Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations