Texturize a GAN Using a Single Image

TL;DR

This paper introduces a method to adapt pre-trained GANs to generate images with textures matching a single reference image, using a novel training approach that balances texture similarity, diversity, and realism.

Contribution

It presents a novel single-image texture adaptation technique for GANs, combining patch and laplacian adversarial losses to achieve realistic, diverse textured image generation.

Findings

Successfully matches textures of reference images

Maintains diversity and realism in generated images

Effective adaptation with a single reference image

Abstract

Can we customize a deep generative model which can generate images that can match the texture of some given image? When you see an image of a church, you may wonder if you can get similar pictures for that church. Here we present a method, for adapting GANs with one reference image, and then we can generate images that have similar textures to the given image. Specifically, we modify the weights of the pre-trained GAN model, guided by the reference image given by the user. We use a patch discriminator adversarial loss to encourage the output of the model to match the texture on the given image, also we use a laplacian adversarial loss to ensure diversity and realism, and alleviate the contradiction between the two losses. Experiments show that the proposed method can make the outputs of GANs match the texture of the given image as well as keep diversity and realism.