TextSR super-resolves multilingual scene text by conditioning a diffusion model on UTF-8-encoded OCR characters, achieving top OCR accuracy on TextZoom and on small/medium text in a self-defined TextVQA evaluation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance
TextSR super-resolves multilingual scene text by conditioning a diffusion model on UTF-8-encoded OCR characters, achieving top OCR accuracy on TextZoom and on small/medium text in a self-defined TextVQA evaluation.