facebookresearch / IMGUR5K-Handwriting-Dataset
IMGUR5K handwriting set. It is a handwritten in-the-wild dataset, which contains challenging real world handwritten samples from different writers.The dataset is shared as a set of image urls with annotations. This code downloads the images and verifies the hash to the image to avoid data contamination.
☆283Updated 6 months ago
Related projects: ⓘ
- ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)☆264Updated 3 years ago
- [CVPR 2021] Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach☆244Updated 9 months ago
- A pytorch implementation of the SRNet architecture from the paper Editing text in the wild (Liang Wu et al.)☆150Updated last year
- [CVPR 2020] STEFANN: Scene Text Editor using Font Adaptive Neural Network (official code).☆259Updated 4 months ago
- [CVPR 2022] Aesthetic Text Logo Synthesis via Content-aware Layout Inferring☆262Updated 2 years ago
- A tensorflow reproducing of paper “Editing Text in the wild”☆225Updated 4 years ago
- The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.☆344Updated 2 months ago
- A hybrid dataset for document unwarping (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)☆160Updated last year
- Code for BMVC2020 paper "Text and Style Conditioned GAN for Generation of Offline Handwriting Lines"☆66Updated last year
- Our implementation of Text Style Brush architecture.☆116Updated 7 months ago
- Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)☆490Updated last year
- [SIGGRAPH 2020] Attribute2Font: Creating Fonts You Want From Attributes☆226Updated 2 years ago
- Its a implementation of DeepFont : Identify Your Font from An Image using Keras☆210Updated 3 weeks ago
- Code and data for ECCV 2020 paper Generating Handwriting via Decoupled Style Descriptors☆53Updated 2 years ago
- EnsNet: Ensconce Text in the Wild☆123Updated 4 years ago
- ☆321Updated 4 years ago
- Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021☆475Updated 3 months ago
- An application of high resolution GANs to dewarp images of perturbed documents☆121Updated 2 years ago
- ☆54Updated 2 years ago
- Attention-based sequence-to-sequence model for handwritten word recognition☆55Updated last year
- ☆47Updated last year
- Distorted Document Images dataset (DDI-100).☆125Updated last year
- Document Rectification and Illumination Correction using a Patch-based CNN☆338Updated last year
- Handwritten Text Generation☆19Updated 3 years ago
- Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network☆159Updated last year
- OCR dataset Text-Detection dataset Font-Classification dataset generator☆134Updated 2 years ago
- This is a data generator of SRNet which is the model of paper Editing Text in the wild.☆103Updated last year
- PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)☆287Updated 5 months ago
- ☆32Updated last year
- Document Image Enhancement with GANs - TPAMI journal☆175Updated last year