EriCongMa / awesome-transformer-ocr
This repository is created to share current progress of transformer based optical character recognition(OCR). Welcome to share~
☆44Updated 11 months ago
Related projects: ⓘ
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆144Updated 3 weeks ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆121Updated 10 months ago
- Contrast-guided Feature Adjustment Module for Visual Information Extraction☆28Updated last year
- Official implementation for Dessurt☆56Updated last year
- [ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)☆36Updated 11 months ago
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆48Updated 2 years ago
- An unofficial Implementation of DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents☆32Updated last year
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆38Updated 5 months ago
- ☆37Updated 2 months ago
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆113Updated last year
- DocILE: Document Information Localization and Extraction Benchmark☆116Updated 4 months ago
- ☆40Updated 2 years ago
- Table Structure Recognition☆52Updated last year
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆69Updated 3 years ago
- A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers☆52Updated last week
- ☆17Updated last year
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipedia☆23Updated last year
- Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)☆116Updated 10 months ago
- OCR Annotations from Amazon Textract for Industry Documents Library☆99Updated 2 years ago
- CTE: Contextualized Table Extraction Dataset☆17Updated last year
- A curated list of papers about key information extraction.☆72Updated last month
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 2 years ago
- Datasets and Evaluation Scripts for CompHRDoc☆19Updated 5 months ago
- A large scale camera-taken table detection and recognition dataset.☆107Updated 11 months ago
- ☆52Updated 8 months ago
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆79Updated last year
- ☆12Updated 2 months ago
- Code for ICCV 2023 Paper : “ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction”☆50Updated last year
- A PyTorch implementation of DTrOCR: Decoder-only Transformer for Optical Character Recognition☆42Updated last month
- [ICDAR 2023] (Oral) An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation☆69Updated last week