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.
☆51Updated this week
Related projects ⓘ
Alternatives and complementary repositories for shabby-pages
- DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022☆141Updated 2 months ago
- [ICDAR 2023] (Oral) An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation☆70Updated 2 months ago
- Document Image Binarization☆73Updated last month
- ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation☆127Updated last week
- Inference, training and evaluation code for our models from the paper "Inv3D: a high-resolution 3D invoice dataset for template-guided si…☆42Updated 9 months ago
- ☆41Updated 11 months ago
- A function that takes as input a cropped text line image, and outputs the dewarped image.☆16Updated 2 weeks ago
- The official code for “Geometric Representation Learning for Document Image Rectification”, ECCV, 2022.☆76Updated 4 months ago
- A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping☆101Updated 2 years ago
- Code for the paper "UVDoc: Neural Grid-based Document Unwarping"☆82Updated 3 months ago
- ☆72Updated last year
- Official code for DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degra…☆22Updated 3 months ago
- A PyTorch implementation of DTrOCR: Decoder-only Transformer for Optical Character Recognition☆92Updated 3 months ago
- ☆77Updated last year
- Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network☆166Updated last year
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆165Updated this week
- ☆25Updated last year
- The official implementation of SPTS v2: Single-Point Text Spotting☆126Updated last year
- An application of high resolution GANs to dewarp images of perturbed documents☆125Updated 3 years ago
- Attention-based sequence-to-sequence model for handwritten word recognition☆56Updated last month
- Code from our paper "Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction " (ICCVW) 2023.☆25Updated 9 months ago
- A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers☆55Updated 2 months ago
- ☆69Updated last year
- [MM'2024] Official implementation of "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Ext…☆24Updated last month
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆41Updated 7 months ago
- [ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)☆38Updated last year
- ☆17Updated 2 years ago
- ☆13Updated 4 months ago
- Pytorch implementation and extension of "DocUnet: Document Image Unwarping via A Stacked U-Net"☆105Updated 4 years ago
- Synthesize distorted document image and control points.☆42Updated 2 years ago