A Closed-form Solution to Universal Style Transfer

by   Ming Lu, et al.

Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of VGG network as the encoders and trains several decoders to invert the features into images. Therefore, the effect of style transfer is achieved by feature transform. Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing. In this paper, we first propose a novel interpretation by treating it as the optimal transport problem. Then, we demonstrate the relations of our formulation with former works like Adaptive Instance Normalization (AdaIN) and Whitening and Coloring Transform (WCT). Finally, we derive a closed-form solution under our formulation by additionally considering the content loss of Gatys. Comparatively, our solution can preserve better structure and achieve visually pleasing results. It is simple yet effective and we demonstrate the advantages both quantitatively and qualitatively. Besides, we hope our theoretical analysis can inspire future works in neural style transfer.


page 6

page 7

page 8


Universal Style Transfer via Feature Transforms

Universal style transfer aims to transfer arbitrary visual styles to con...

Demystifying Neural Style Transfer

Neural Style Transfer has recently demonstrated very exciting results wh...

Wasserstein Style Transfer

We propose Gaussian optimal transport for Image style transfer in an Enc...

Style-Aware Normalized Loss for Improving Arbitrary Style Transfer

Neural Style Transfer (NST) has quickly evolved from single-style to inf...

In the light of feature distributions: moment matching for Neural Style Transfer

Style transfer aims to render the content of a given image in the graphi...

CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

Content affinity loss including feature and pixel affinity is a main pro...

Conditional Neural Style Transfer with Peer-Regularized Feature Transform

This paper introduces a neural style transfer model to conditionally gen...

Please sign up or login with your details

Forgot password? Click here to reset