TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution

T1Covered by 1 source · first reported by arXiv at 25 Sept, 04:00 UTC

arXiv:2609.29240v1 Announce Type: cross Abstract: Text image super-resolution (TSR) aims to recover visually faithful and readable text under unknown degradations. Existing diffusion-based methods typically rely on multi-step prediction of either the high-resolution image or its text prior…

science

Sources

• T1TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-ResolutionarXiv25 Sept, 04:00