GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

A Deep Learning based project for colorizing and restoring old images (and video!)

Tool to moniter social distancing using CCTV feeds, videos. Can be used at public places and workplace.

Avatars for Zoom, Skype and other video-conferencing apps.

A webcam-based 3x3x3 rubik's cube solver written in Python 3 and OpenCV.

Pytorch implementation of MixNMatch

Cross-platform, customizable ML solutions for live and streaming media.

EyeLoop is a Python 3-based eye-tracker tailored specifically to dynamic, closed-loop experiments on consumer-grade hardware.

Dim and brighten the screen based on whether you are present with OpenCV

🏀🤖🏀 AI web app and API to analyze basketball shots and shooting pose.

Image Classifier with Flask and Keras CNN

GAN Lab: An Interactive, Visual Experimentation Tool for Generative Adversarial Networks

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

This repo finds free parking spaces in the parking lot using only image processing

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code

ImageBind One Embedding Space to Bind Them All

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

A Python package for fast and robust Image Stitching

Reads your hand signs and translates them to English words using Tensorflow object detection API

Official Code for DragGAN (SIGGRAPH 2023)

one-click face swap

[CVPR2024] DisCo: Referring Human Dance Generation in Real World

Segment Anything in High Quality [NeurIPS 2023]

We write your reusable computer vision tools. 💜

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation