Computer Vision
Showing 36 of 261 projects
A robust LiDAR odometry pipeline that works out-of-the-box without parameter tuning for accurate robot localization.
A comprehensive C++ toolkit for mobile robotics and computer vision research, providing libraries for SLAM, Bayesian filtering, and 3D geometry.
A web/desktop application for collaborative labeling and annotation of images, text, audio, documents, and other data types.
A C++ library for real-time metric-semantic SLAM, building semantically annotated 3D meshes from camera and IMU data.
A PHP library for generating perceptual image hashes to detect similar or duplicate images.
A C library for efficient image processing and analysis, widely used in OCR and computer vision applications.
An unsupervised learning framework for depth and ego-motion estimation from monocular videos using TensorFlow.
A deep learning-based facial detection library for Python with facial landmark extraction.
A pure Python computer vision library based on the book 'Programming Computer Vision with Python'.
A web-based labeling tool for creating semantic segmentation training data from 2D images and 3D point clouds.
A curated collection of datasets for Simultaneous Localization and Mapping (SLAM) research, categorized by topic, platform, and environment.
![[Web]](/_next/image?url=https%3A%2F%2Fgithub.com%2Fs9xie.png%3Fsize%3D40&w=96&q=75){kind=small}
A deep learning-based edge detection algorithm using holistically-nested fully convolutional neural networks.
A Python library implementing multiple alpha matting algorithms for extracting foreground objects from images.
A computer vision library for human-computer interaction, focusing on head pose estimation, gaze direction, skin detection, motion tracking, and saliency mapping using CNNs.
An end-to-end deep learning system for reconstructing complete 3D scenes (geometry and semantics) from posed 2D images.
A pure Go implementation that finds optimal image crops for arbitrary aspect ratios using content-aware analysis.
A smart and easy-to-use image masking and cutout SDK for iOS and iPadOS mobile applications.
A real-time baseline 3D multi-object tracking system using LiDAR point clouds, combining 3D Kalman filter and Hungarian algorithm.
A modular C++ library implementing the Iterative Closest Point (ICP) algorithm for aligning 2D and 3D point clouds in robotics and computer vision.
A pure Go library providing a comprehensive set of image processing filters with no external dependencies.
An end-to-end 3D object detection network that uses deep point set networks and Hough voting to directly detect objects in point clouds.
A realtime LiDAR odometry and mapping (LOAM) method for state estimation and mapping using 3D lidar sensors like Velodyne VLP16.
React Native binding for iOS ARKit, enabling augmented reality app development with 3D components and plane detection.
A ROS package for extrinsic calibration between LiDAR and camera sensors using 3D-3D point correspondences.
TensorFlow implementation of YOLO for real-time object detection using pretrained YOLO_small, YOLO_tiny, and YOLO_face models.
An open-source, near photo-realistic 3D simulation platform for training and evaluating embodied AI agents.
An open-source computer vision tool that detects, tracks, and counts moving objects from cameras and videos.
A curated checklist of state-of-the-art research materials (datasets, papers, code) for interaction-aware trajectory prediction.
A deep learning pipeline for 3D object detection from RGB-D data by combining 2D detectors with PointNet-based 3D processing.
An open-source C library with MATLAB interfaces implementing popular computer vision algorithms for image understanding and local feature extraction.
A collection of high-performance GICP-based point cloud registration algorithms with multi-threaded and GPU-accelerated implementations.
A real-time monocular SLAM system for computing camera trajectories and sparse 3D scene reconstruction.
A lightweight C++/Python library for 3D data processing, geometry algorithms, and rendering with an easy-to-use API.
A general-purpose PyTorch codebase for 3D object detection with state-of-the-art model implementations and multi-dataset support.
Official repository for Big Transfer (BiT) models, providing pre-trained visual representations for efficient transfer learning across computer vision tasks.
An efficient neural network for semantic segmentation of large-scale 3D point clouds using random sampling.
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.