Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

TL;DR

This paper introduces a real-time arbitrary style transfer method using adaptive instance normalization, enabling flexible and fast style transfer with user controls, overcoming previous limitations of fixed styles and slow optimization.

Contribution

The paper proposes a novel adaptive instance normalization layer that allows a single neural network to perform arbitrary style transfer in real-time.

Findings

Achieves real-time style transfer with arbitrary styles.

Provides flexible user controls like content-style trade-off and style interpolation.

Maintains speed comparable to fixed-style methods.

Abstract

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.