cvg/Hierarchical-Localization

Features

• Visual Localization - Determines a camera's exact position and orientation by matching live images against a 3D reference model.
• 3D Pose Estimation - Calculates precise camera position and orientation by solving the transformation between 2D points and 3D coordinates.
• Visual Localization Frameworks - Provides a complete system for determining camera poses by matching 2D features against 3D reference models.
• Pose Refinement Pipelines - Refines camera pose by progressing from global retrieval to local matching and 3D model alignment.
• Visual Feature Extractors - Uses neural networks to generate robust image descriptors stable across different lighting and viewpoints.
• Feature Extraction - Identifies local keypoints and descriptors from images using deep learning and traditional computer vision.
• Deep Feature Extractors - Identifies local keypoints and descriptors in images using neural network based computer vision.
• Pose Estimation - Calculates the precise location and angle of a device within a mapped environment using visual features.
• Structure From Motion - Generates sparse 3D models from unordered image sets to serve as reference maps for localization.
• Local Feature Matching - Establishes geometric correspondences between images using local descriptors and RANSAC verification.
• Image Retrieval Systems - Filters large image databases using high-level feature vectors to identify candidate reference images.
• Large-Scale Image Retrieval - Uses global descriptors to quickly identify the most relevant reference images from a large database.
• Camera Calibration - Defines camera intrinsic parameters to ensure accuracy in 3D reconstruction and pose estimation.
• Simultaneous Localization and Mapping - Modular toolbox for 6-DOF visual localization.

Star history