OCR-based Text Recognition on OpenLibrary (test)
56.17APTextDiffuser-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 | 56.17 | 38.16 | 42.42 | 29.16 | |
| GlyphControl-10MPre-defined Text Layout=true, Training Data Size=10M, Training Data Source=LAION-Glyph2024.06 | 47.34 | 37.62 | 38.36 | 25.34 | |
| TextDiffuser-7MPre-defined Text Layout=true, Training Data Size=7M, Training Data Source=MARIO-7M2024.06 | 42.57 | 31.46 | 33.18 | 21.08 | |
| SceneTextGen-7MPre-defined Text Layout=false, Training Data Size=7M, Training Data Source=MARIO-7M2024.06 | 41.36 | 45.19 | 39.45 | 25.71 | |
| ControlNetPre-defined Text Layout=true2024.06 | 40.5 | 42.73 | 36.9 | 24.15 | |
| DeepFloydPre-defined Text Layout=false2024.06 | 25.55 | 39.1 | 26.35 | 16.1 | |
| Latent Diffusion ModelPre-defined Text Layout=false2024.06 | 19.11 | 28.73 | 19.23 | 11.06 |