Unified Style Transfer
arXiv:2110.10481
Abstract
Currently, it is hard to compare and evaluate different style transfer algorithms due to chaotic definitions of style and the absence of agreed objective validation methods in the study of style transfer. In this paper, a novel approach, the Unified Style Transfer (UST) model, is proposed. With the introduction of a generative model for internal style representation, UST can transfer images in two approaches, i.e., Domain-based and Image-based, simultaneously. At the same time, a new philosophy based on the human sense of art and style distributions for evaluating the transfer model is presented and demonstrated, called Statistical Style Analysis. It provides a new path to validate style transfer models' feasibility by validating the general consistency between internal style representation and art facts. Besides, the translation-invariance of AdaIN features is also discussed.
arXiv comment9 pages, 5 figures
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Learned Representation For Artistic Style
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
- Convolutional Sketch Inversion
- Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
- Artist Style Transfer Via Quadratic Potential