Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
This provides a more efficient solution for artists and designers needing real-time texture synthesis and style transfer, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the slow optimization process of Gatys et al.'s texture and style transfer method by training compact feed-forward convolutional networks, achieving comparable quality but hundreds of times faster generation.
Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods requires a slow and memory-consuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image. The resulting networks are remarkably light-weight and can generate textures of quality comparable to Gatys~et~al., but hundreds of times faster. More generally, our approach highlights the power and flexibility of generative feed-forward models trained with complex and expressive loss functions.