sparkfish / shabby-pages
ShabbyPages is a state-of-the-art corpus of born-digital document images with both ground truth and distorted versions appropriate for use in training models to reverse distortions and recover to original denoised documents.
☆48Updated this week
Related projects: ⓘ
- [ICDAR 2023] (Oral) An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation☆69Updated last week
- DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022☆139Updated 2 weeks ago
- ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation☆120Updated 2 months ago
- Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation☆151Updated 6 months ago
- A PyTorch implementation of DTrOCR: Decoder-only Transformer for Optical Character Recognition☆42Updated last month
- OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR☆30Updated 3 weeks ago
- Easter2.0: IMPROVING CONVOLUTIONAL MODELS FOR HANDWRITTEN TEXT RECOGNITION☆75Updated last year
- ☆34Updated 9 months ago
- ☆12Updated 2 months ago
- ☆74Updated last year
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆79Updated last year
- ☆71Updated last year
- Document Image Binarization☆71Updated 3 weeks ago
- Table detection (TD) and table structure recognition (TSR) using Yolov5/Yolov8, cand you can get the same (even better) result compared w…☆35Updated 2 months ago
- ☆62Updated 11 months ago
- Official code for DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degra…☆19Updated last month
- https://dl.acm.org/doi/10.1145/3657281☆85Updated 4 months ago
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆38Updated 5 months ago
- A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers☆52Updated last week
- The official code for “Geometric Representation Learning for Document Image Rectification”, ECCV, 2022.☆71Updated last month
- Inference, training and evaluation code for our models from the paper "Inv3D: a high-resolution 3D invoice dataset for template-guided si…☆39Updated 7 months ago
- A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping☆100Updated last year
- A large scale camera-taken table detection and recognition dataset.☆107Updated 11 months ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆144Updated 3 weeks ago
- ☆62Updated 9 months ago
- Pytorch implementation and extension of "DocUnet: Document Image Unwarping via A Stacked U-Net"☆101Updated 4 years ago
- This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadow, dew…☆149Updated last week
- A function that takes as input a cropped text line image, and outputs the dewarped image.☆15Updated 2 weeks ago
- Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network☆159Updated last year
- Attention-based sequence-to-sequence model for handwritten word recognition☆55Updated last year