To comprehensively evaluate the effectiveness and generalization ability of style transfer methods, we build StyleBench that covers 73 distinct styles, ranging from paintings, flat illustrations, 3D rendering to sculptures with varying materials. For each style, we collect 5-7 distinct images with variations.
In total, our StyleBench contains 490 images across diverse styles.
Variants: StyleBench
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Style Transfer | StyleShot | StyleShot: A Snapshot on Any … | 2024-07-01 |
| Style Transfer | StyleID | Style Injection in Diffusion: A … | 2023-12-11 |
| Style Transfer | InST | Inversion-Based Style Transfer with Diffusion … | 2022-11-23 |
| Style Transfer | CAST | Domain Enhanced Arbitrary Image Style … | 2022-05-19 |
| Style Transfer | EFDM | Exact Feature Distribution Matching for … | 2022-03-15 |
| Style Transfer | StrTR-2 | StyTr$^2$: Image Style Transfer with … | 2022-01-01 |
| Style Transfer | AdaAttN | AdaAttN: Revisit Attention Mechanism in … | 2021-08-08 |
Recent papers with results on this dataset: