Computer Vision
Showing 36 of 711 projects
A curated list of research papers, datasets, and resources for anomaly detection in time-series, video, and image data.
A Swift framework for GPU-accelerated image and video processing on Apple platforms using Metal.
An interactive online learning platform for computer vision with a comprehensive Chinese ebook, code, and community.
An open-source, programmable machine vision camera platform that runs Python and supports AI models like TensorFlow.
A deep learning project using Keras to build convolutional and recurrent neural networks for high-accuracy captcha recognition.
Convert Caffe deep learning models to TensorFlow format for deployment and inference.
A Python toolkit for working with the nuScenes and nuImages autonomous driving datasets, providing data loading, visualization, and evaluation utilities.
A curated collection of hands-on data science project ideas and resources for learning machine learning and AI concepts.
A lightweight portable library for OpenGL display, interaction, and video input abstraction, widely used in computer vision prototyping.
A real-time monocular SLAM system that creates large-scale semi-dense maps using a fully direct approach without feature extraction.
A curated collection of academic papers, code, and resources for learning with noisy labels in machine learning.
A benchmarking suite comparing the performance of public convolutional neural network implementations across multiple deep learning frameworks.
A curated list of key papers and resources on implicit neural representations, a novel approach to parameterizing signals as continuous functions.
A collection of beginner-friendly TensorFlow tutorials using Jupyter Notebook, covering deep learning fundamentals and practical applications.
An open-source deep learning API and server written in C++ that supports multiple backends like PyTorch, TensorRT, and TensorFlow for training and inference.
A Go library that simplifies TensorFlow's Go bindings with method chaining, automatic scoping, and type conversion.
Rust bindings for the OpenCV computer vision library, enabling Rust developers to leverage OpenCV's capabilities.
A direct sparse odometry library for real-time monocular visual SLAM, estimating camera motion from image sequences.
A ROS package for real-time object detection in camera images using YOLO (V3) on GPU and CPU.
A ROS package for real-time object detection in camera images using YOLO (V3) on GPU and CPU.
A clean, simplified implementation of the LOAM algorithm for real-time LiDAR odometry and mapping using Eigen and Ceres Solver.
A pioneering object detection system that combines region proposals with convolutional neural network features, significantly advancing detection accuracy.
A C++ library for fast approximate nearest neighbor searches in high-dimensional spaces with automatic algorithm selection.
A fast, comprehensive, and dependency-free image processing library for Node.js with native bindings.
A Java library for accessing integrated or USB webcams with a simple API and support for multiple capture frameworks.
A curated collection of papers, code, and resources on neural rendering techniques for computer vision and graphics.
An efficient probabilistic 3D mapping framework based on octrees for robotics and computer vision applications.
A large-scale dataset of object-centric video clips with 3D bounding box annotations and AR metadata for 3D object detection research.
A Swift camera system for iOS providing easy integration, customizable media capture, and image streaming.
A set of Vue.js components for detecting and decoding QR codes and other barcodes directly in the browser.
A generalist algorithm for cellular segmentation with human-in-the-loop training and superhuman generalization across diverse microscopy images.
A curated list of datasets, tools, methods, review papers, and competitions for remote sensing change detection.
A robust LiDAR odometry pipeline that works out-of-the-box without parameter tuning for accurate robot localization.
A high-performance C++ image processing and machine learning library optimized with SIMD instructions across multiple CPU architectures.
A dataset of 129.6 million computer-generated building footprint polygons for the United States, derived from satellite imagery.
An open source Python library and framework for building computer vision models on satellite, aerial, and large imagery sets.
Related Tags
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.