Animation engine for explanatory math videos

real time face swap and one-click video deepfake with only a single image

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

pix2tex: Using a ViT to convert images of equations into LaTeX code.

Synthesizing and manipulating 2048x1024 images with conditional GANs

Handwriting Synthesis with RNNs ✏️

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

NeuroKit2: The Python Toolbox for Neurophysiological Signal Processing

Text page dewarping using a "cubic sheet" model

A Python package to stabilize videos using OpenCV

A flexible source separation library in Python

Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)

A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".

Deep Convolutional Neural Networks for Musical Source Separation

[AAAI' 25] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

An easy-to-use library for skin tone classification

This repository contains the codes to replicate the simulations from the paper: "Wav-KAN: Wavelet Kolmogorov-Arnold Networks". It showcases the use of wavelet functions in neural networks to improv…

Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems [ICML'25]

Eulerian Video Magnification for colors and motions magnification

An open source python library for non-linear piecewise symbolic regression based on Genetic Programming

Pytorch implementation for pixel-wise scene text segmentation based on DeepLabV3+

This repository contains the code for Multiclass Segmentation on the human faces using Landmark Guided Face Parsing (LaPa) dataset in TensorFlow.

Digital Video Processing Graduate Course Homeworks

A face segmentation implementation of FarRL model (CVPR 2022) using Facer, a face analysis toolkit for modern research.

Opensource tracking and image stabilization tool

The DMVAnet architecture is a deep learning network that achieves state of the art performance for the document image binarization task