PDF documents are widely used for sharing information since they preserve formatting and quality across various devices. However, when it comes to editing PDFs, things aren’t always convenient. Many ...
Our long-term goal is to build efficient and reliable 2.5B diffusion-based decoding for document OCR. MinerU-Diffusion reframes document OCR as an inverse rendering problem and replaces slow, ...
Quick PDF OCR is a Chrome extension that runs OCR locally on PDF files and generates a searchable text-based PDF while trying to preserve the original outline/bookmarks.