ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

A collection of resources on Sports Camera Calibration

ONNX-compatible DeDoDe 🎶 Detect, Don't Describe - Describe, Don't Detect, for Local Feature Matching. Supports TensorRT 🚀

Homography Decomposition Networks for Planar Object Tracking

This is the official repo for the CVPR 2021 IMW paper: "Perceptual Loss for Robust Unsupervised Homography Estimation"

Graduation Project. Vehicle speed estimation using computer vision and evolutionary-based camera calibration

Vision-based GNSS-Free Localization for UAVs in the Wild

This repo contains a curative list of homography estimation, image alignment and related application.

Implementation of Panorama stitching using ORB feature matching, and RANSAC for homography estimation, and stitching using Image pyramids.

FPGA implementation of the Image stitching using FAST. For CPU implementation visit tharaka27-ImageStitcherFAST.

This repository contains an implementation of panorama stitching, a computer vision technique used to combine multiple images into a seamless panoramic image. The project leverages classical techniques such as feature detection, matching, and RANSAC, along with a deep learning approach using Homography Net and Tensor DLT.

Feature matching (SIFT) between two images and then applying normalized linear homography estimation, robustified by standard RANSAC

Repository contains applications that can 1. estimate homography matrix and annotate minion images on empty billboards; 2. Estimate Depth using Sum of Squared Distance and Cross Correlation Metrics as well as improve the results using Viterbi Algorithm. Error in Estimated Depth Map is also measured quantitatively against Ground Truth Images.

Finds corner features in multiple images and aligns the images in a mosaic by estimating a homography between corresponding features

Stitches two or more images to form image panorama.

Autopano - Stirching multiple images to form a seamless panorama

Simple exercise for image stitching

Stabilo is a Python package for stabilizing video frames or object trajectories using advanced transformation techniques. It supports user-defined masks to exclude specific areas, making it ideal for dynamic scenes with moving objects. Unlike traditional stabilization, it stabilizes content relative to a chosen reference frame.

Implementation of an homography algorithm for computer vision