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 101110 of 134 papers

TitleStatusHype
Co-Attention for Conditioned Image Matching0
Robust Homography Estimation via Dual Principal Component Pursuit0
GPO: Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization0
Deep Exposure Fusion with Deghosting via Homography Estimation and Attention Learning0
G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data0
Neural Outlier Rejection for Self-Supervised Keypoint LearningCode0
DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration0
Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction0
Content-Aware Unsupervised Deep Homography EstimationCode0
UnsuperPoint: End-to-end Unsupervised Interest Point Detector and DescriptorCode0
Show:102550
← PrevPage 11 of 14Next →

No leaderboard results yet.