Style Transfer Dataset: What Makes A Good Stylization?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929644605800448 |
|---|---|
| author | Kitov, Victor Abramov, Valentin Akhtyrchenko, Mikhail |
| author_facet | Kitov, Victor Abramov, Valentin Akhtyrchenko, Mikhail |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17139 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Style Transfer Dataset: What Makes A Good Stylization? Kitov, Victor Abramov, Valentin Akhtyrchenko, Mikhail Computer Vision and Pattern Recognition Image and Video Processing 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. |
| title | Style Transfer Dataset: What Makes A Good Stylization? |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2412.17139 |