Repository History
10 repositories tagged with computer-vision
Roboflow Notebooks: Master State-of-the-Art Computer Vision Models
Roboflow Notebooks offers a comprehensive collection of tutorials designed to help users master state-of-the-art computer vision models and techniques. This repository covers a wide range of topics, from foundational architectures like ResNet to cutting-edge models such as RF-DETR, YOLO11, SAM 3, and Qwen3-VL. It serves as an invaluable resource for anyone looking to explore and implement advanced computer vision solutions.
gaussian-splatting: Real-Time 3D Radiance Field Rendering
gaussian-splatting is the original reference implementation for real-time radiance field rendering. This repository introduces a novel approach using 3D Gaussians for high-quality, real-time novel-view synthesis at 1080p resolution, offering significant advancements in computer graphics and vision. Developed by GRAPHDECO Inria, it provides a robust framework for 3D scene reconstruction and interactive visualization.
PyMatting: A Python Library for Alpha Matting
PyMatting is a powerful Python library designed for alpha matting, a technique used to accurately extract foreground objects from images. It offers implementations of various matting algorithms and foreground estimation methods, making it a versatile tool for image processing tasks. The library also provides GPU support for enhanced performance and integrates seamlessly with popular scientific computing packages.
Lazyeat: Hands-Free Control with Gesture Recognition for Seamless Interaction
Lazyeat is an innovative, open-source project that provides a contactless control tool based on advanced gesture recognition. It allows users to interact with their devices using simple hand gestures and voice commands, eliminating the need for physical contact. This tool is particularly useful for situations where your hands might be dirty, such as while eating, enabling seamless control over media playback, web browsing, and more.
Rerun: Open Source SDK for Multimodal Data Logging and Visualization
Rerun is an open-source SDK designed for logging, storing, querying, and visualizing complex multimodal and multi-rate data. It provides SDKs for C++, Python, and Rust, enabling developers to stream data to a powerful viewer for live visualization or later analysis. This tool is particularly valuable for debugging and understanding systems in robotics, computer vision, and spatial AI.
NVIDIA Isaac GR00T: A Foundation Model for Generalist Robots
NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) foundation model designed for generalized humanoid robot skills. It enables robots to perform manipulation tasks in diverse environments by taking multimodal input, including language and images. Researchers and professionals can leverage this model for fine-tuning on custom datasets and deploying it for inference.
DragGAN: Interactive Point-Based Image Manipulation with Generative AI
DragGAN is the official code for the SIGGRAPH 2023 paper, "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold." This powerful Python-based repository enables users to precisely control and manipulate generated images using interactive dragging points. It offers an intuitive way to edit AI-generated content, making complex image transformations accessible.
pytorch-deep-learning: Learn PyTorch for Deep Learning from Zero to Mastery
This repository provides comprehensive materials for the "Learn PyTorch for Deep Learning: Zero to Mastery" course. It offers a hands-on, code-first approach to mastering PyTorch, covering fundamentals to advanced topics like computer vision and model deployment. With over 16,000 stars, it's a highly popular resource for beginners in machine learning and deep learning.
face-cropper: Advanced Face Cropping with Mediapipe and OpenCV
The `face-cropper` repository offers a robust Python solution for extracting faces from images. It implements a custom pipeline leveraging Mediapipe's FaceDetection and FaceMesh networks to accurately crop, optionally remove backgrounds, and correct the roll of detected faces. This tool is ideal for pre-processing images in computer vision tasks or real-time applications.
jscanify: The Javascript Document Scanning Library
jscanify is a powerful Javascript library designed for document scanning, offering features such as paper detection, distortion correction, glare suppression, and multi-colored paper support. Built with `opencv.js`, it provides robust capabilities for web, NodeJS, and React environments, making it a versatile tool for various applications.