paper-with-me

Papers Homography Estimation

“Homography Estimation” 태그가 달린 논문 148편 · 필터 해제

HOME: Robust Hough-space Matching Method for Structured and Textureless Videos

2026-07-28 · Masaki Satoh arxiv

Visual front-ends for robotic localization typically rely on point-based features such as Oriented FAST and Rotated BRIEF (ORB), which frequently fail in structured environments dominated by strong linear structures or t…

Homography Estimation3D Pose Estimation

On the Geometry of Learned Representations in Event-Based Multi-Modal Egomotion Estimation

2026-07-17 · Stefano Silvestrini, Michele Ceresoli arxiv

Classical approaches to event-based egomotion estimation, including those adopted by the top-performing teams of the ELOPE challenge, rely on geometric optimization frameworks such as contrast maximization, homography es…

Homography Estimation

SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios

2026-06-29 · Shangxuan Xie, Haifeng Wu, Yuhang Wang, Huarong Jia 외 arxiv

Homography estimation, as one of the fundamental problems in computer vision, remains challenged by scale variation scenarios where image pairs potentially exhibit significant scale discrepancies. Existing deep learning …

Homography Estimation

SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation

2026-04-15 · Songlin Du, Xiaoyong Lu, Yaping Yan, Guobao Xiao 외 arxiv

Local feature matching plays a critical role in understanding the correspondence between cross-view images. However, traditional methods are constrained by the inherent local nature of feature descriptors, limiting their…

Homography EstimationVisual LocalizationPose EstimationImage Matching

Mathematical Analysis of Image Matching Techniques

2026-04-08 · Oleh Samoilenko arxiv

Image matching is a fundamental problem in Computer Vision with direct applications in robotics, remote sensing, and geospatial data analysis. We present an analytical and experimental evaluation of classical local featu…

Homography EstimationKeypoint DetectionImage Matching

CM-Bench: A Comprehensive Cross-Modal Feature Matching Benchmark Bridging Visible and Infrared Images

2026-03-13 · Liangzheng Sun, Mengfan He, Xingyu Shao, Binbin Li 외 arxiv

Infrared-visible (IR-VIS) feature matching plays an essential role in cross-modality visual localization, navigation and perception. Along with the rapid development of deep learning techniques, a number of representativ…

Homography EstimationVisual LocalizationPose EstimationImage Matching

Towards Generalized Multimodal Homography Estimation

2026-03-04 · Jinkun You, Jiaxin Cheng, Jie Zhang, Yicong Zhou arxiv

Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modal…

Homography Estimation

High Dynamic Range Imaging Based on an Asymmetric Event-SVE Camera System

2026-02-28 · Pengju Sun, Banglei Guan, Jing Tao, Zhenbao Yu 외 arxiv

High dynamic range (HDR) imaging under extreme illumination remains challenging for conventional cameras due to overexposure. Event cameras provide microsecond temporal resolution and high dynamic range, while spatially …

Homography Estimation

Admittance-Based Motion Planning with Vision-Guided Initialization for Robotic Manipulators in Self-Driving Laboratories

2026-01-29 · Shifa Sulaiman, Tobias Jensen, Francesco Schetter, Simon Bøgh arxiv

Self driving laboratories (SDLs) are highly automated research environments that leverage advanced technologies to conduct experiments and analyze data with minimal human involvement. These environments often involve del…

Homography EstimationMotion PlanningPose Estimation

HomoFM: Deep Homography Estimation with Flow Matching

2026-01-26 · Mengfan He, Liangzheng Sun, Chunyu Li, Ziyang Meng arxiv

Deep homography estimation has broad applications in computer vision and robotics. Remarkable progresses have been achieved while the existing methods typically treat it as a direct regression or iterative refinement pro…

Homography EstimationDomain Adaptation

ShelfRectNet: Single View Shelf Image Rectification with Homography Estimation

2025-11-25 · Onur Berk Tore, Ibrahim Samil Yalciner, Server Calap arxiv

Estimating homography from a single image remains a challenging yet practically valuable task, particularly in domains like retail, where only one viewpoint is typically available for shelf monitoring and product alignme…

Homography Estimation

LeCoT: revisiting network architecture for two-view correspondence pruning

2025-11-10 · Luanyuan Dai, Xiaoyu Du, Jinhui Tang arxiv

Two-view correspondence pruning aims to accurately remove incorrect correspondences (outliers) from initial ones and is widely applied to various computer vision tasks. Current popular strategies adopt multilayer percept…

Homography EstimationVisual LocalizationPose Estimation

Radially Distorted Homographies, Revisited

2025-08-28 · Mårten Wadenbäck, Marcus Valtonen Örnhag, Johan Edstedt arxiv

Homographies are among the most prevalent transformations occurring in geometric computer vision and projective geometry, and homography estimation is consequently a crucial step in a wide assortment of computer vision t…

Homography Estimation

GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry

2025-08-01 · Jiajun Le, Jiayi Ma arxiv

Recent progress in two-view geometry increasingly emphasizes enforcing smoothness and global consistency priors when estimating motion fields between pairs of images. However, in complex real-world scenes, characterized …

Homography Estimation

HomographyAD: Deep Anomaly Detection Using Self Homography Learning

2025-06-10 · Jongyub Seok, Chanjin Kang

Anomaly detection (AD) is a task that distinguishes normal and abnormal data, which is important for applying automation technologies of the manufacturing facilities. For MVTec dataset that is a representative AD dataset…

Anomaly DetectionHomography Estimation

Deep Learning Reforms Image Matching: A Survey and Outlook

2025-06-05 · Shihua Zhang, Zizhuo Li, Kaining Zhang, Yifan Lu 외

Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visu…

3D ReconstructionDeep LearningHomography EstimationSimultaneous Localization and Mapping+2

Words as Geometric Features: Estimating Homography using Optical Character Recognition as Compressed Image Representation

2025-05-25 · Ross Greer, Alisha Ukani, Katherine Izhikevich, Earlence Fernandes 외

Document alignment and registration play a crucial role in numerous real-world applications, such as automated form processing, anomaly detection, and workflow automation. Traditional methods for document alignment rely …

Anomaly DetectionHomography EstimationOptical Character RecognitionOptical Character Recognition (OCR)

Decoupled Geometric Parameterization and its Application in Deep Homography Estimation

2025-05-22 · Yao Huang, Si-Yuan Cao, Yaqing Ding, Hao Yin 외

Planar homography, with eight degrees of freedom (DOFs), is fundamental in numerous computer vision tasks. While the positional offsets of four corners are widely adopted (especially in neural network predictions), this …

Homography Estimation

LiftFeat: 3D Geometry-Aware Local Feature Matching

2025-05-06 · Yepeng Liu, Wenpeng Lai, Zhou Zhao, Yuxuan Xiong 외

Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminativ…

3D geometryDepth EstimationHomography EstimationMonocular Depth Estimation+2

CodingHomo: Bootstrapping Deep Homography With Video Coding

2025-04-16 · Yike Liu, Haipeng Li, Shuaicheng Liu, Bing Zeng

Homography estimation is a fundamental task in computer vision with applications in diverse fields. Recent advances in deep learning have improved homography estimation, particularly with unsupervised learning approaches…

Homography Estimation
1–20 / 148 다음 →