P$^2$-GAN: Efficient Style Transfer Using Single Style Image

TL;DR

P$^2$-GAN introduces a novel approach for style transfer that learns from a single style image using patch permutation and a specialized discriminator, achieving high-quality results efficiently.

Contribution

The paper proposes P$^2$-GAN, a new model that learns artistic styles from just one image via patch permutation and a patch discriminator, improving efficiency and quality.

Findings

Produces finer style transfer quality from a single image.

Achieves better computational efficiency than existing methods.

Effectively captures local style patterns with patch-based training.

Abstract

Style transfer is a useful image synthesis technique that can re-render given image into another artistic style while preserving its content information. Generative Adversarial Network (GAN) is a widely adopted framework toward this task for its better representation ability on local style patterns than the traditional Gram-matrix based methods. However, most previous methods rely on sufficient amount of pre-collected style images to train the model. In this paper, a novel Patch Permutation GAN (P$^2$-GAN) network that can efficiently learn the stroke style from a single style image is proposed. We use patch permutation to generate multiple training samples from the given style image. A patch discriminator that can simultaneously process patch-wise images and natural images seamlessly is designed. We also propose a local texture descriptor based criterion to quantitatively evaluate the style transfer quality. Experimental results showed that our method can produce finer quality re-renderings from single style image with improved computational efficiency compared with many state-of-the-arts methods.