P$^2$-GAN: Efficient Style Transfer Using Single Style Image
This addresses the need for efficient style transfer in image synthesis, particularly for applications with limited style data, though it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of style transfer requiring many style images by proposing P^2-GAN, which learns from a single style image using patch permutation and a patch discriminator, achieving finer quality re-renderings with improved computational efficiency compared to state-of-the-art methods.
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.