SOTAVerified

Homography Estimation

Homography estimation is a technique used in computer vision and image processing to find the relationship between two images of the same scene, but captured from different viewpoints. It is used to align images, correct for perspective distortions, or perform image stitching. In order to estimate the homography, a set of corresponding points between the two images must be found, and a mathematical model must be fit to these points. There are various algorithms and techniques that can be used to perform homography estimation, including direct methods, RANSAC, and machine learning-based approaches.

Papers

Showing 2130 of 134 papers

TitleStatusHype
PnLCalib: Sports Field Registration via Points and Lines OptimizationCode2
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV0
NeRF-Supervised Feature Point Detection and DescriptionCode0
Deep Homography Estimation for Visual Place RecognitionCode2
Are Semi-Dense Detector-Free Methods Good at Matching Local Features?0
Noisy One-point Homographies are Surprisingly Good0
MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography EstimationCode1
Video-based Sequential Bayesian Homography Estimation for Soccer Field RegistrationCode0
Automated Camera Calibration via Homography Estimation with GNNs0
FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer0
Show:102550
← PrevPage 3 of 14Next →

No leaderboard results yet.