OCR-based Text Recognition on TMDB (test)
44.01APTextDiffuser-10M
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| TextDiffuser-10MPre-defined Text Layout=true, Training Data Size=10M, Training Data Source=Expanded (MARIO-7M, MARIO-TMDB, MARIO-OpenLibrary)2024.06 | 44.01 | 42.43 | 39.94 | 28.89 | |
| SceneTextGen-7MPre-defined Text Layout=false, Training Data Size=7M, Training Data Source=MARIO-7M2024.06 | 38.13 | 47.16 | 37.9 | 26.02 | |
| GlyphControl-10MPre-defined Text Layout=true, Training Data Size=10M, Training Data Source=LAION-Glyph2024.06 | 36.35 | 40.82 | 34.57 | 23.62 | |
| TextDiffuser-7MPre-defined Text Layout=true, Training Data Size=7M, Training Data Source=MARIO-7M2024.06 | 31.98 | 33.62 | 29.61 | 19.3 | |
| ControlNetPre-defined Text Layout=true2024.06 | 30.75 | 46.67 | 32.84 | 21.94 | |
| DeepFloydPre-defined Text Layout=false2024.06 | 22.84 | 37.38 | 24.49 | 15 | |
| Latent Diffusion ModelPre-defined Text Layout=false2024.06 | 17.17 | 25.79 | 17.03 | 9.74 |