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 4150 of 134 papers

TitleStatusHype
Patch2Pix: Epipolar-Guided Pixel-Level CorrespondencesCode1
DUT: Learning Video Stabilization by Simply Watching Unstable VideosCode1
Geometric Estimation via Robust Subspace RecoveryCode1
Making Affine Correspondences Work in Camera Geometry ComputationCode1
Online Invariance Selection for Local Feature DescriptorsCode1
SEKD: Self-Evolving Keypoint Detection and DescriptionCode1
Deep Homography Estimation for Dynamic ScenesCode1
CONSAC: Robust Multi-Model Fitting by Conditional Sample ConsensusCode1
MAGSAC: marginalizing sample consensusCode1
SuperPoint: Self-Supervised Interest Point Detection and DescriptionCode1
Show:102550
← PrevPage 5 of 14Next →

No leaderboard results yet.