Awesome GitHub RepositoriesVisual Stream Processing

MODNet is a deep learning image segmenter and portrait matting model designed to isolate human subjects from backgrounds. It generates high-quality alpha mattes for images and video using only standard RGB input, removing the requirement for manual trimap guides. The framework is optimized for real-time inference and provides utilities to export pre-trained model weights into specialized formats for deployment on target hardware. The project covers the full workflow for portrait isolation, including supervised matting model training on labeled datasets, real-time video background removal, an

OpenGlass is an AI smart glasses framework and microcontroller hardware project designed to turn standard eyewear into computer vision wearables. It provides a system for integrating wearable camera sensors with multimodal AI to process visual data in real time. The project enables the development of AI-powered glasses that can identify people and objects, translate visual text, and record life events. It connects off-the-shelf electronic components to mobile software and large language models for visual analysis. The system covers a range of capabilities including real-time visual stream pr

This project is a web-based platform designed for benchmarking, visualizing, and evaluating computer vision algorithms focused on image feature extraction and matching. It provides a unified interface to compare the performance and accuracy of different models by processing image pairs or live video streams. The system distinguishes itself through a modular architecture that allows users to define custom processing pipelines and register external algorithms via configuration files. It incorporates geometric verification techniques to refine visual data and improve the precision of detected co