DocsaidLab / DocAlignerLinks
Predictions of the four corners of documents.
☆42Updated 3 months ago
Alternatives and similar repositories for DocAligner
Users that are interested in DocAligner are comparing it to the libraries listed below
Sorting:
- Inference, training and evaluation code for our models from the paper "Inv3D: a high-resolution 3D invoice dataset for template-guided si…☆51Updated last year
- ☆36Updated last year
- Code for the paper "UVDoc: Neural Grid-based Document Unwarping"☆165Updated last year
- Document Dewarping with Control Points☆182Updated 3 years ago
- The code and the DIW dataset for "Learning From Documents in the Wild to Improve Document Unwarping" (SIGGRAPH 2022)☆135Updated last year
- ☆88Updated 8 months ago
- Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network☆184Updated 2 years ago
- Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation☆203Updated 4 months ago
- ☆62Updated last year
- Synthesize distorted document image and control points.☆50Updated 3 years ago
- Real-time detection of documents in images☆83Updated last year
- ☆61Updated last year
- The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.☆401Updated 3 months ago
- This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadowing, …☆301Updated last month
- Document Rectification and Illumination Correction using a Patch-based CNN☆388Updated 3 years ago
- DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022☆173Updated 8 months ago
- DocTr++ in PaddlePaddle☆56Updated last year
- Code from our paper "Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction " (ICCVW) 2023.☆26Updated last year
- [MM'2024] PEneo, an effective algorithm for key-value pair extraction from form-like documents, designed for real-world applications.☆37Updated 6 months ago
- [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild☆45Updated last month
- The official implementation of SPTS v2: Single-Point Text Spotting☆138Updated 2 years ago
- Synthetic identity documents dataset☆27Updated 7 months ago
- ☆78Updated 2 years ago
- A Pytorch Implementation of HED (Holistically-Nested Edge Detection algorithm) for Document Detection☆50Updated 6 years ago
- An implementation of "CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model".☆144Updated 6 months ago
- ☆66Updated last year
- ☆18Updated 2 years ago
- A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping☆106Updated 2 years ago
- CRAFT(Baek et al., 2019) model training code☆50Updated last year
- ☆41Updated 3 years ago