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 5160 of 134 papers

TitleStatusHype
Geometrized Transformer for Self-Supervised Homography EstimationCode1
SiLK: Simple Learned Keypoints0
A Large-Scale Homography Benchmark0
Recurrent Homography Estimation Using Homography-Guided Image Warping and Focus TransformerCode1
AbHE: All Attention-based Homography Estimation0
Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence ConstraintCode1
Rethinking Low-level Features for Interest Point Detection and DescriptionCode1
ASpanFormer: Detector-Free Image Matching with Adaptive Span TransformerCode2
SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation0
A Gis Aided Approach for Geolocalizing an Unmanned Aerial System Using Deep LearningCode1
Show:102550
← PrevPage 6 of 14Next →

No leaderboard results yet.