Papers › A Closed-form Solution to Universal Style Transfer

A Closed-form Solution to Universal Style Transfer

3 Jun 2019ICCV 2019 10arXiv:1906.00668archive 2025-07-28

Ming Lu, Hao Zhao, Anbang Yao, Yurong Chen, Feng Xu, Li Zhang

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 named Optimal Style Transfer (OST) 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 its advantages both quantitatively and qualitatively. Besides, we hope our theoretical analysis can inspire future works in neural style transfer. Code is available at https://github.com/lu-m13/OptimalStyleTransfer.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lu-m13/OptimalStyleTransfer officialmentioned in papermentioned on GitHubpytorch report
boomb0om/pytorch-optimalstyletransfer mentioned on GitHubpytorch report
lu-m13/optimal mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

FormStyle Transfer

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adaptive Instance NormalizationConvolutionDense ConnectionsDropoutInstance NormalizationMax PoolingReLUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections