sparkfish / shabby-pagesLinks
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.
☆62Updated 10 months ago
Alternatives and similar repositories for shabby-pages
Users that are interested in shabby-pages are comparing it to the libraries listed below
Sorting:
- ☆65Updated 2 years ago
- DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022☆181Updated last year
- ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation☆154Updated 8 months ago
- [ICDAR 2023] (Oral) An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation☆76Updated last year
- The official code for “Geometric Representation Learning for Document Image Rectification”, ECCV, 2022.☆88Updated 7 months ago
- ☆44Updated last year
- [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild☆51Updated 4 months ago
- Inference, training and evaluation code for our paper "DocMatcher: Document Image Dewarping via Structural and Textual Line Matching" (WA…☆46Updated 6 months ago
- Inference, training and evaluation code for our models from the paper "Inv3D: a high-resolution 3D invoice dataset for template-guided si…☆57Updated last year
- Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation☆205Updated 8 months ago
- A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping☆106Updated 3 years ago
- Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network☆191Updated 3 years ago
- ☆89Updated 11 months ago
- [MM'2024] PEneo, an effective algorithm for key-value pair extraction from form-like documents, designed for real-world applications.☆39Updated 9 months ago
- ☆10Updated 7 months ago
- The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.☆417Updated 7 months ago
- Easter2.0: IMPROVING CONVOLUTIONAL MODELS FOR HANDWRITTEN TEXT RECOGNITION☆79Updated 2 years ago
- A function that takes as input a cropped text line image, and outputs the dewarped image.☆21Updated 4 months ago
- Synthesize distorted document image and control points.☆51Updated 3 years ago
- Pytorch implementation and extension of "DocUnet: Document Image Unwarping via A Stacked U-Net"☆116Updated 5 years ago
- ☆60Updated 3 years ago
- Document Image Binarization☆79Updated last year
- The code and the DIW dataset for "Learning From Documents in the Wild to Improve Document Unwarping" (SIGGRAPH 2022)☆137Updated last year
- Code for the paper "UVDoc: Neural Grid-based Document Unwarping"☆187Updated last year
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆44Updated last year
- The official implementation of SPTS v2: Single-Point Text Spotting☆141Updated 2 years ago
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆80Updated 3 years ago
- Attention-based sequence-to-sequence model for handwritten word recognition☆63Updated last year
- Code from our paper "Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction " (ICCVW) 2023.☆27Updated last year
- An application of high resolution GANs to dewarp images of perturbed documents☆150Updated 4 years ago