Computer Vision
Showing 36 of 711 projects
A C++ implementation of the SEEDS superpixel segmentation algorithm using energy-driven sampling for computer vision.
Adobe AIR native extension for Microsoft Kinect v2 SDK, enabling body tracking and sensor data access in Flash/AIR applications.
An easy-to-use PyTorch library for faster computer vision model development and training.
A PyTorch-based framework providing implementations of state-of-the-art deep learning models for computer vision tasks.
A CGImage extension that uses Apple's Vision Framework to detect and center faces in images.
Deploy a neural network model that transfers artistic styles from one image to another using a ResNet-based architecture.
A lightweight, header-only C++11 deep neural network library designed for embedded systems with minimal dependencies.
A curated collection of resources, datasets, and methods for 3D LiDAR-based Moving Object Segmentation (MOS) research.
A Godot engine module for real-time head tracking using OpenCV with GPU acceleration for immersive 3D perspective.
An open-source solution for the Google AI Open Images Object Detection Challenge, providing a RetinaNet-based benchmark with experiment tracking.
A collection of neural network models ported from torchvision for use with JAX and Flax.
Code for the CIFAR-10 Kaggle competition using cuda-convnet for image classification.
A JAX-based library for fast, composable image augmentation with geometric and color transformations.
A library of reusable web components for data annotation tasks in computer vision applications.
A lightweight JavaScript/WebGL library for real-time face detection, depth estimation, and 3D face insertion in the browser.
ROS2 node for interfacing with Raspberry Pi camera modules using the MMAL rawcam component (deprecated).
A pre-trained image classifier that recognizes 365 different scene and location types using a ResNet18 model fine-tuned on Places365.
TensorFlow implementation of AlexNet with 3D convolutional layers for volumetric image recognition.
Estimates horizon lines from single images using deep learning models trained on diverse outdoor scenes.
An attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remote sensing images.
A Python tool that extracts network structures from 2D images and outputs them as weighted undirected planar graphs.
A Rust library for extracting dominant colors from images with zero external dependencies.
A collection of easy-to-use machine learning datasets for Torch7 with built-in preprocessing and sampling utilities.
Python API for communicating with and configuring the Onion Tau LiDAR Camera to retrieve depth, greyscale, and amplitude data.
A TensorFlow/TensorLayer implementation of Spatial Transformer Networks for learning image transformations like scaling, cropping, and rotation.
A cross-framework, cross-platform computer vision and image manipulation library for Haxe.
A convolutional neural network solution for the GalaxyZoo galaxy classification challenge, achieving 9th place with a score of 0.08246.
A foundation model-driven method for semantic cell classification in whole slide images, extending Cellpose with a WSI workflow and QuPath integration.
Detects objects in real-time using Firebase ML Kit and displays 3D AR labels via ARKit and SceneKit.
A ROS-based player for replaying the KiTTI autonomous driving dataset with point cloud, image, and ground truth publishing.
Examples and libraries for the IN2AR augmented reality SDK, demonstrating AR capabilities and integration.
Interactive tutorial for learning face detection and recognition with hands-on code samples using local AI.
An open-source image processing tool for histological image preprocessing and augmentation to improve deep learning model development.
Python-based vision processing for FRC robots to detect and track reflective tape targets using a Raspberry Pi and camera.
A curated collection of resources, papers, and implementations for training Generative Adversarial Networks (GANs).
A TensorFlow-based image segmentation model that assigns each pixel in an image to one of 21 object classes from the PASCAL VOC dataset.
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.