seungjun45 / Water-Filling
My second year project under advisor Prof. Changick Kim (2015.09~2016.03). The technique is for removing illumination distortions for camera captured document images. Source Code Available
☆35Updated 4 years ago
Related projects: ⓘ
- Repository for Intrinsic Decomposition of Document Images In-the-Wild (BMVC '20)☆44Updated last year
- [ACM MM 2020] Exploring Font-independent Features for Scene Text Recognition☆44Updated 3 years ago
- ☆35Updated 2 years ago
- TIoU metric in python3. Forked from https://github.com/Yuliang-Liu/TIoU-metric.☆24Updated 4 years ago
- Geometric Rectification of Document Images using Adversarial Gated Unwarping Network☆25Updated 4 years ago
- Pytorch implements SA-Text: Simple but Accurate Detector for Text of Arbitrary Shapes☆43Updated 4 years ago
- Project code for ACM MM2020 paper: "TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection"☆47Updated 11 months ago
- ☆56Updated 5 months ago
- An unofficial implementation of DocUNet☆65Updated 4 years ago
- Synthesize distorted document image and control points.☆39Updated 2 years ago
- Improving Scene Text Image Super-Resolution via Dual Prior Modulation Network (AAAI 2023)☆48Updated last month
- ☆87Updated 4 years ago
- A Validation Set for Text Detection Ambiguity☆36Updated 3 years ago
- This is a data generator of SRNet which is the model of paper Editing Text in the wild.☆103Updated last year
- ☆68Updated 3 years ago
- EnsNet: Ensconce Text in the Wild☆123Updated 4 years ago
- A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping☆100Updated last year
- Code and Dataset for our paper: Layout-Aware Single-Image Document Flattening☆15Updated 2 weeks ago
- Code for Text Prior Guided Scene Text Image Super-Resolution (TIP 2023)☆135Updated 9 months ago
- ☆18Updated 3 years ago
- ☆25Updated last year
- ☆24Updated 3 years ago
- This repository is the implementation of "Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contex…☆77Updated last year
- ABCNet_Chinese☆52Updated 3 years ago
- This dataset contains re-annotations of 4 popular Latin/English scene text recognition datasets.☆48Updated 4 years ago
- Blender rendering codes for doc3D-dataset (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)☆110Updated 2 years ago
- ICDAR 2019☆25Updated 5 years ago
- Unofficial implementation of ''BEDSR-Net: A Deep Shadow Removal from a Single Document Image'' with PyTorch☆54Updated 2 years ago
- PERT: A Progressively Region-based Network for Scene Text Removal (TIP2023)☆32Updated last year
- ☆16Updated 4 years ago