Style Transfer Dataset: What Makes A Good Stylization?

Victor Kitov, Valentin Abramov, Mikhail Akhtyrchenko
12/22/2024
cs.CVeess.IV

No confident code implementation found for this paper.

Abstract

We present a new dataset with the goal of advancing image style transfer - the task of rendering one image in the style of another image. The dataset covers various content and style images of different size and contains 10.000 stylizations manually rated by three annotators in 1-10 scale. Based on obtained ratings, we find which factors are mostly responsible for favourable and poor user evaluations and show quantitative measures having statistically significant impact on user grades. A methodology for creating style transfer datasets is discussed. Presented dataset can be used in automating multiple tasks, related to style transfer configuration and evaluation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

OmniStyle: Filtering High Quality Style Transfer Data at Scale

88% match2 repos622026

D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods

85% match1 repo132024

CSGO: Content-Style Composition in Text-to-Image Generation

85% match1 repo3912024

InstantStyleGaussian: Efficient Art Style Transfer with 3D Gaussian Splatting

84% match2024

StyleBrush: Style Extraction and Transfer from a Single Image

84% match2024

Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning

83% match1 repo42024

Cite this paper

@article{kitov2024style,
  title  = {Style Transfer Dataset: What Makes A Good Stylization?},
  author = {Victor Kitov and Valentin Abramov and Mikhail Akhtyrchenko},
  year   = {2024},
  eprint = {2412.17139},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.17139v1}
}

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/2412.17139.svg)](https://codeofpaper.com/paper/2412.17139)

Discussion