facebookresearch / IMGUR5K-Handwriting-DatasetLinks
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.
☆298Updated last year
Alternatives and similar repositories for IMGUR5K-Handwriting-Dataset
Users that are interested in IMGUR5K-Handwriting-Dataset are comparing it to the libraries listed below
Sorting:
- ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)☆276Updated 5 years ago
- [CVPR 2020] STEFANN: Scene Text Editor using Font Adaptive Neural Network (official code).☆272Updated last year
- Code for BMVC2020 paper "Text and Style Conditioned GAN for Generation of Offline Handwriting Lines"☆73Updated 2 years ago
- [CVPR 2021] Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach☆268Updated 2 years ago
- document image degradation☆163Updated 5 years ago
- A pytorch implementation of the SRNet architecture from the paper Editing text in the wild (Liang Wu et al.)☆170Updated 7 months ago
- Source code for ECCV20 "GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images"☆74Updated 4 years ago
- Code and data for ECCV 2020 paper Generating Handwriting via Decoupled Style Descriptors☆58Updated 3 years ago
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆90Updated 4 years ago
- Its a implementation of DeepFont : Identify Your Font from An Image using Keras☆265Updated last year
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks☆186Updated 2 years ago
- Our implementation of Text Style Brush architecture.☆136Updated last year
- [SIGGRAPH 2020] Attribute2Font: Creating Fonts You Want From Attributes☆231Updated 3 years ago
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…☆339Updated last year
- ☆60Updated 3 years ago
- ☆321Updated 5 years ago
- Distorted Document Images dataset (DDI-100).☆143Updated 3 years ago
- Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)☆588Updated last year
- Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021☆559Updated last year
- The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.☆414Updated 5 months ago
- Attention-based sequence-to-sequence model for handwritten word recognition☆62Updated last year
- ☆193Updated last year
- Handwriting-Transformers (ICCV21)☆234Updated last year
- ICDAR 2019: MaskRCNN on PubLayNet datasets. Paragraph detection, table detection, figure detection,...☆182Updated 4 years ago
- A tensorflow reproducing of paper “Editing Text in the wild”☆233Updated 6 years ago
- ☆120Updated 4 years ago
- Document Rectification and Illumination Correction using a Patch-based CNN☆391Updated 3 years ago
- A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping☆106Updated 3 years ago
- DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation☆128Updated 2 years ago
- [CVPR 2022] Aesthetic Text Logo Synthesis via Content-aware Layout Inferring☆274Updated 3 years ago