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 3140 of 134 papers

TitleStatusHype
Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography EstimatorCode1
Scene-Aware Feature Matching0
Homography Estimation in Complex Topological Scenes0
AffineGlue: Joint Matching and Robust Estimation0
KP2Dtiny: Quantized Neural Keypoint Detection and Description on the EdgeCode0
LightGlue: Local Feature Matching at Light SpeedCode4
S2LD: Sparse-to-Local-Dense Matching for Geometry-Guided Correspondence EstimationCode1
Pentagon-Match (PMatch): Identification of View-Invariant Planar Feature for Local Feature Matching-Based Homography Estimation0
SIDAR: Synthetic Image Dataset for Alignment & RestorationCode0
Attention Weighted Local DescriptorsCode1
Show:102550
← PrevPage 4 of 14Next →

No leaderboard results yet.