Homography Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 12
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection
FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images
Explicit homography estimation improves contrastive self-supervised learning
Real-Time Facial Expression Emoji Masking with Convolutional Neural Networks and Homography
Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
DUT: Learning Video Stabilization by Simply Watching Unstable Videos
Homography Estimation with Convolutional Neural Networks Under Conditions of Variance
HSolo: Homography from a single affine aware correspondence
Making Affine Correspondences Work in Camera Geometry Computation
Online Invariance Selection for Local Feature Descriptors
Co-Attention for Conditioned Image Matching
SEKD: Self-Evolving Keypoint Detection and Description
GPO: Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization
Deep Exposure Fusion with Deghosting via Homography Estimation and Attention Learning
Deep Homography Estimation for Dynamic Scenes
G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data
CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus
Neural Outlier Rejection for Self-Supervised Keypoint Learning
DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration
Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction
Content-Aware Unsupervised Deep Homography Estimation
UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor
Homography from two orientation- and scale-covariant features
STN-Homography: estimate homography parameters directly
Optimal Multi-view Correction of Local Affine Frames
Generative Adversarial Frontal View to Bird View Synthesis
Full explicit consistency constraints in uncalibrated multiple homography estimation
MAGSAC: marginalizing sample consensus
Insights into the robustness of control point configurations for homography and planar pose estimation
Latent RANSAC
SuperPoint: Self-Supervised Interest Point Detection and Description
Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model
STag: A Stable Fiducial Marker System
Geometric Multi-Model Fitting with a Convex Relaxation Algorithm
Planar Object Tracking in the Wild: A Benchmark
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.