Homography Estimation
52 papers with code • 4 benchmarks • 7 datasets
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.
MS COCO
S-COCO
YUD+
POT-210
NYU-VP
PDS-COCO
VidSet
Most implemented papers
A Large Scale Homography Benchmark
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation
Shiaoming/ALIKED
•
•
Image keypoints and descriptors play a crucial role in many visual measurement tasks.
LightGlue: Local Feature Matching at Light Speed
We introduce LightGlue, a deep neural network that learns to match local features across images.
STag: A Stable Fiducial Marker System
Jitter impairs robustness in vision and robotics applications, and deteriorates the sense of presence and immersion in AR/VR applications.
Latent RANSAC
We present a method that can evaluate a RANSAC hypothesis in constant time, i. e. independent of the size of the data.
Optimal Multi-view Correction of Local Affine Frames
The technique requires the epipolar geometry to be pre-estimated between each image pair.
Rethinking Planar Homography Estimation Using Perspective Fields
ruizengalways/PFNet
•
•
ACCV 2018 2019
In addition, the new parameterization of this task is general and can be implemented by any fully convolutional network (FCN) architecture.
Homography from two orientation- and scale-covariant features
Two new general constraints are derived on the scales and rotations which can be used in any geometric model estimation tasks.
Content-Aware Unsupervised Deep Homography Estimation
JirongZhang/DeepHomography
•
•
ECCV 2020
Homography estimation is a basic image alignment method in many applications.
Deep Homography Estimation for Dynamic Scenes
We then develop a multi-scale neural network and show that when properly trained using our new dataset, this neural network can already handle dynamic scenes to some extent.
