AutoHDR restores full pages of damaged historical documents by combining OCR damage detection, LLM-based text prediction, and patch-autoregressive image diffusion, improving OCR accuracy on severely damaged documents from 46.83% to 84.05%.
https://www.cbeta.org/ https://www.cbeta.org/
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
-
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration
AutoHDR restores full pages of damaged historical documents by combining OCR damage detection, LLM-based text prediction, and patch-autoregressive image diffusion, improving OCR accuracy on severely damaged documents from 46.83% to 84.05%.