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 4150 of 134 papers

TitleStatusHype
Analyzing the Domain Shift Immunity of Deep Homography EstimationCode0
SiLK -- Simple Learned KeypointsCode2
ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable TransformationCode2
Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial VideoCode0
Medical Image Analysis using Deep Relational Learning0
PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment0
Nonlinear constructive observer design for direct homography estimation0
ParaFormer: Parallel Attention Transformer for Efficient Feature Matching0
A Large Scale Homography BenchmarkCode2
GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning0
Show:102550
← PrevPage 5 of 14Next →

No leaderboard results yet.