Stars
OCR, layout analysis, reading order, table recognition in 90+ languages
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
Foundational Models for State-of-the-Art Speech and Text Translation
Extract and Merge image patches for easy, fast and self-contained digital image processing and deep learning model training.
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Inpaint anything using Segment Anything and inpainting models.
SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
Code for our CVPR 2022 paper 'Generalized Category Discovery'. Project page: https://www.robots.ox.ac.uk/~vgg/research/gcd/
A playbook for systematically maximizing the performance of deep learning models.
OpenMMLab Detection Toolbox and Benchmark
Semantic Instance Segmentation with a Discriminative Loss Function in PyTorch
A simple, fully convolutional model for real-time instance segmentation.
cheat allows you to create and view interactive cheatsheets on the command-line. It was designed to help remind *nix system administrators of options for commands that they use frequently, but not …
Python library for converting Python calculations into rendered latex.
Compute Vanishing points using RANSAC and rectify the image
Label Studio is a multi-type data labeling and annotation tool with standardized output format
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
How to create custom COCO data set for instance segmentation
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Convert text into beautiful artistic images
Text detection with mainly MSER and SWT
SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]
TextBoxes++: A Single-Shot Oriented Scene Text Detector