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 150 of 134 papers

TitleStatusHype
LightGlue: Local Feature Matching at Light SpeedCode4
LiftFeat: 3D Geometry-Aware Local Feature MatchingCode3
Deep Homography Estimation for Visual Place RecognitionCode2
STHN: Deep Homography Estimation for UAV Thermal Geo-localization with Satellite ImageryCode2
ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable TransformationCode2
SiLK -- Simple Learned KeypointsCode2
PnLCalib: Sports Field Registration via Points and Lines OptimizationCode2
A Large Scale Homography BenchmarkCode2
ASpanFormer: Detector-Free Image Matching with Adaptive Span TransformerCode2
Unsupervised Homography Estimation with Coplanarity-Aware GANCode1
Space-Partitioning RANSACCode1
Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence ConstraintCode1
UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localizationCode1
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating OptimizationCode1
SuperPoint: Self-Supervised Interest Point Detection and DescriptionCode1
Vehicle Speed Estimation Using Computer Vision And Evolutionary Camera CalibrationCode1
S2LD: Sparse-to-Local-Dense Matching for Geometry-Guided Correspondence EstimationCode1
MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography EstimationCode1
MAGSAC: marginalizing sample consensusCode1
Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace ProjectionCode1
Patch2Pix: Epipolar-Guided Pixel-Level CorrespondencesCode1
Rethinking Low-level Features for Interest Point Detection and DescriptionCode1
Geometric Estimation via Robust Subspace RecoveryCode1
CONSAC: Robust Multi-Model Fitting by Conditional Sample ConsensusCode1
SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised LearningCode1
SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split OptimizationCode1
Adapting Dense Matching for Homography Estimation with Grid-based AccelerationCode1
Deep Homography Estimation for Dynamic ScenesCode1
EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut PhotographyCode1
DUT: Learning Video Stabilization by Simply Watching Unstable VideosCode1
Iterative Deep Homography EstimationCode1
Depth-Aware Multi-Grid Deep Homography Estimation with Contextual CorrelationCode1
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor ExtractionCode1
Good Keypoints for the Two-View Geometry Estimation ProblemCode1
Attention Weighted Local DescriptorsCode1
Deep Image Homography EstimationCode1
3DG-STFM: 3D Geometric Guided Student-Teacher Feature MatchingCode1
TVCalib: Camera Calibration for Sports Field Registration in SoccerCode1
A Gis Aided Approach for Geolocalizing an Unmanned Aerial System Using Deep LearningCode1
Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography EstimatorCode1
Making Affine Correspondences Work in Camera Geometry ComputationCode1
MatchFormer: Interleaving Attention in Transformers for Feature MatchingCode1
InterNet: Unsupervised Cross-modal Homography Estimation Based on Interleaved Modality Transfer and Self-supervised Homography PredictionCode1
Online Invariance Selection for Local Feature DescriptorsCode1
Perceptual Loss for Robust Unsupervised Homography EstimationCode1
Recurrent Homography Estimation Using Homography-Guided Image Warping and Focus TransformerCode1
Line as a Visual Sentence: Context-aware Line Descriptor for Visual LocalizationCode1
SEKD: Self-Evolving Keypoint Detection and DescriptionCode1
Geometrized Transformer for Self-Supervised Homography EstimationCode1
Visual SLAM with Graph-Cut Optimized Multi-Plane ReconstructionCode1
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.