SOTA Document Image Enhancement - T2T-BinFormer: Effective Document Image Enhancement Using tokens-to-token Transformer Network

[WACV 2025] High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

Repository containing unpaper build for Windows users.

[APSIPA ASC 2025] MFE-GAN: Efficient GAN-based Framework for Document Image Enhancement and Binarization with Multi-scale Feature Extraction

A collection of document enhancement methods.

Automatically remove brand logos and unwanted slides from PDFs

[TCE] DocUnfold: Leveraging Unfolding Network and A Real-World Large-Scale Dataset for Handwriting Contamination Removal in Documents

NeuroScan-AI is an advanced document-understanding engine built with modern computer vision and OCR pipelines. It performs smart perspective correction, illumination normalization, and adaptive enhancement to transform raw camera captures into clean, searchable, professional-grade documents.

Learning lab about Damaged Document Analysis and Historical Document Enhancement