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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 134 papers

TitleStatusHype
Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial VideoCode0
Medical Image Analysis using Deep Relational Learning—0
PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment—0
Nonlinear constructive observer design for direct homography estimation—0
ParaFormer: Parallel Attention Transformer for Efficient Feature Matching—0
GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning—0
SiLK: Simple Learned Keypoints—0
A Large-Scale Homography Benchmark—0
AbHE: All Attention-based Homography Estimation—0
SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation—0
Warped Convolutional Networks: Bridge Homography to sl(3) algebra by Group Convolution—0
Towards a Unified Approach to Homography Estimation Using Image Features and Pixel IntensitiesCode0
Road-aware Monocular Structure from Motion and Homography Estimation—0
Pixel-wise Deep Image Stitching—0
Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion ExtractionCode0
Precise Aerial Image Matching based on Deep Homography Estimation—0
LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation—0
Galois/monodromy groups for decomposing minimal problems in 3D reconstruction—0
Localization of Ice-Rink for Broadcast Hockey Videos—0
FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images—0
Explicit homography estimation improves contrastive self-supervised learning—0
A Robust and Efficient Framework for Sports-Field Registration—0
Real-Time Facial Expression Emoji Masking with Convolutional Neural Networks and HomographyCode0
Homography Estimation with Convolutional Neural Networks Under Conditions of Variance—0
HSolo: Homography from a single affine aware correspondence—0
Show:102550
← PrevPage 4 of 6Next →

No leaderboard results yet.