Style Transfer by Relaxed Optimal Transport and Self-Similarity

Nicholas Kolkin, Jason Salavon, Greg Shakhnarovich
4/29/2019
cs.CV

Official code: nkolkin13/STROTSS (312 stars, last commit 2023-12-07).

Abstract

Style transfer algorithms strive to render the content of one image using the style of another. We propose Style Transfer by Relaxed Optimal Transport and Self-Similarity (STROTSS), a new optimization-based style transfer algorithm. We extend our method to allow user-specified point-to-point or region-to-region control over visual similarity between the style image and the output. Such guidance can be used to either achieve a particular visual effect or correct errors made by unconstrained style transfer. In order to quantitatively compare our method to prior work, we conduct a large-scale user study designed to assess the style-content tradeoff across settings in style transfer algorithms. Our results indicate that for any desired level of content preservation, our method provides higher quality stylization than prior work. Code is available at https://github.com/nkolkin13/STROTSS

View on arXivView PDF

Code Implementations(1)

nkolkin13/STROTSSOfficial100%

Style Transfer by Relaxed Optimal Transport and Self-Similarity (CVPR 2019)

31238PythonApr 29, 20192 years ago

Similar Papers

CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer

90% match1 repo2062022

D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods

89% match1 repo132024

Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate

89% match1 repo1012023

TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer

89% match1 repo72023

Universal Style Transfer via Feature Transforms

89% match1 repo6082017

SEM-CS: Semantic CLIPStyler for Text-Based Image Style Transfer

89% match2023

Cite this paper

@article{kolkin2019style,
  title  = {Style Transfer by Relaxed Optimal Transport and Self-Similarity},
  author = {Nicholas Kolkin and Jason Salavon and Greg Shakhnarovich},
  year   = {2019},
  eprint = {1904.12785},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.12785}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.12785.svg)](https://codeofpaper.com/paper/1904.12785)

Discussion