End-to-End Multilingual Optical Character Recognition (OCR) Solution.
This repo contains the implementation for Rethinking Image Mixture for Unsupervised Visual Representation Learning
Attention. A pre-trained model is downloaded from my cloud (which has its limits).
Paired image-to-image translation, trained on synthetic data generated by StyleGAN2 outperforms existing approaches in image manipulation.
Convert images to a string with Google Tesseract and then into a static HTML site using Python
Image, GIF and Video enlarger/upscaler achieved with waifu2x-ncnn-vulkan, waifu2x-converter and Anime4K.
A commandline tool + python library to glitchify images and even make GIFs out of them!
An open source framework for generative image inpainting task, with the support of Contextual Attention (CVPR 2018) and Gated Convolution (ICCV 2019 Oral).
StyleGAN2 - Official TensorFlow Implementation with practical improvements
fast image augmentation library and easy to use wrapper around other libraries.
We introduce the PyMatting package for Python which implements various methods to solve the alpha matting problem.
PaintingLight is a project conducted by the Style2Paints team, aimed at finding a method to manipulate the illumination in digital paintings.
Pytorch implementation of a StyleGAN encoder. Images to latent space representation.
Render images as a set of continuous lines representing each horizontal (or vertical) line of pixels
Modern OpenGL binding for python.
An Adversarial Steganographic Method For Robust, Imperceptible Watermarking.
A script that generates randomized mazes/labyrinths.
In this project, I created an end-to-end solution for large-scale image classification and visual recommendation on fashion images.
A design and implementation of a super lightweight algorithm for "overlapped handwritten signature extraction from scanned documents" using OpenCV and scikit-image on python.
Find the dominant colors in any image.
Load an image file into a numpy array - while automatically rotating the image based on Exif orientation. Prevents upside-down and sideways images!
imagededup is a python package that simplifies the task of finding exact and near duplicates in an image collection.
Deep Image Matting paper implementation in PyTorch.
Automated face warping tool.
This repository contains datasets for multi-object representation learning, used in developing scene decomposition methods like MONet and IODINE.