feature matching and correspondence

This study addresses the insufficient robustness and accuracy of local feature matching in overlapping regions of satellite imagery. To this end, the authors construct a manually curated satellite image dataset annotated with GPS coordinates and conduct a systematic evaluation of SIFT and ORB algorithms across the entire matching pipeline—including keypoint detection, descriptor extraction, feature matching, and RANSAC-based geometric verification. Using the inlier ratio as the primary metric for matching quality, the work quantitatively analyzes the impact of keypoint quantity on matching performance. The results reveal a nonlinear relationship between the number of detected keypoints and the inlier ratio, offering empirical evidence and theoretical guidance for algorithm selection and parameter tuning in remote sensing image matching tasks.

This paper addresses robust point-set matching under outliers and noise. We propose an invariant matching mechanism based on distance profiles, constructing noise- and outlier-robust distance-based feature representations in abstract metric spaces. Theoretically, we establish, for the first time, high-probability guarantees for successful matching, linking our approach to the Gromov–Wasserstein distance and deriving a novel sample complexity upper bound; we further prove that matching success probability grows exponentially with sample size. Experimentally, our method significantly outperforms baselines—including ICP and RANSAC—on synthetic data and diverse real-world benchmarks featuring structural noise, outliers, and non-rigid deformations. Key contributions include: (i) a unified distance-profile modeling framework; (ii) the first theoretical guarantee of joint robustness to both noise and outliers; and (iii) a rigorous analysis of scalability to general metric spaces.

Addressing the challenge of simultaneously achieving robustness, efficiency, and generalization in global point cloud registration, this paper introduces an open-source C++ library. The proposed end-to-end pipeline integrates a lightweight Faster-PFH feature descriptor, a k-core graph-theoretic outlier pruning strategy, and robust pose solvers (e.g., RANSAC and TEASER+). Key contributions include: (i) Faster-PFH, which drastically reduces feature computation overhead while preserving discriminability; (ii) k-core pruning, lowering outlier rejection complexity from O(n²) to near-linear time; and (iii) a modular, highly extensible architecture that maintains high accuracy. Extensive experiments on standard benchmarks—including 3DMatch and KITTI—demonstrate that our method achieves 2–5× speedup over state-of-the-art robust registration approaches, with comparable registration accuracy, while supporting large-scale point clouds and cross-scenario generalization.

In large-scale Structure-from-Motion (SfM), sparse inter-view overlap and drastic viewpoint changes—especially in aerial-to-ground scenarios—lead to low cross-image feature matching density and weak geometric consistency. To address this, we propose a geometry-guided hybrid matching paradigm: (1) geometric verification is formulated as an optimization problem based on Sampson distance; (2) detector-agnostic dense matching is fused with detector-driven sparse anchor guidance, where sparse anchors constrain and enhance the geometric consistency of dense matches; and (3) multi-view geometric consistency is explicitly modeled. Our method significantly improves both matching density and accuracy, outperforming state-of-the-art approaches in extreme large-scale settings. Consequently, camera pose estimation becomes more accurate, and the reconstructed 3D point cloud achieves higher completeness and fidelity.

Existing 3D shape matching methods predominantly assume complete input shapes, while robust partial-observation matching—more reflective of real-world scenarios—remains underexplored. Current benchmarks suffer from limited scale, unrealistic partiality, and absence of cross-dataset ground-truth correspondences. Method: We introduce the first large-scale, standardized benchmark for partial-observation matching: (1) a programmable geometric perturbation framework that synthesizes photorealistic partial deformations with infinite scalability; (2) integration of seven mainstream datasets with manually annotated cross-dataset full-shape correspondences (2,543 pairs); and (3) a multi-level difficulty evaluation protocol. Results: Comprehensive evaluation reveals substantial performance degradation of state-of-the-art methods under realistic partiality. We publicly release the benchmark—including data, baselines, and an open-source evaluation platform—to establish a new standard and accelerate research in partial 3D shape matching.

This work addresses the challenge that existing methods struggle to disambiguate geometrically consistent yet semantically incorrect false inliers in scenes with repetitive structures, textureless regions, or locally similar geometry. To overcome this limitation, the authors propose TriMatch, a novel framework that integrates geometric, textural semantic, and structural semantic features. TriMatch introduces texture–geometry and structure–geometry alignment modules, a semantics-guided correspondence modulation mechanism, and a hierarchical semantic-aware refinement strategy, thereby transcending the constraints of conventional approaches that rely solely on geometric consistency. Experimental results demonstrate that TriMatch significantly outperforms state-of-the-art methods in terms of accuracy, robustness, and generalization capability.

This study addresses the trade-off in image–point cloud registration between insufficient inliers and an excessively high outlier ratio caused by suboptimal point cloud density, which limits registration accuracy. It presents the first systematic analysis of how point cloud density affects cross-modal registration and introduces a cross-coordinate correspondence pruning mechanism. Specifically, coarse correspondences are projected into the image coordinate system, where a lightweight network fuses geometric and feature information to predict inlier confidence scores for effective outlier rejection. Furthermore, a multi-density point cloud ensemble strategy is employed to enhance inlier recall. The proposed method consistently outperforms existing approaches across multiple benchmarks, achieving a registration recall improvement of at least 8.6%.

This work proposes a pixel-accurate epipolar-guided matching method to address the limitations of conventional approaches in challenging scenarios such as repetitive textures or large baselines, where coarse spatial binning introduces errors, necessitates post-processing, and often misses valid correspondences. By leveraging the fundamental matrix to enforce epipolar geometry, the method defines for each keypoint an angular interval derived from a tolerance circle in angle space, transforming the matching problem into a one-dimensional interval query. Efficient exact matching is achieved via a segment tree with logarithmic time complexity. The approach enables per-point tolerance control, eliminates approximation errors and redundant descriptor comparisons, and recovers a complete set of correspondences without post-processing. Evaluated on the ETH3D dataset, it significantly outperforms existing methods, achieving both higher completeness and notable speedup.

PARTE方法通过利用平面结构作为补充注册证据，结合点和平面对应关系进行全局点云配准，解决了因重叠区域有限、重复几何和传感器噪声导致的外点问题。

This study addresses the susceptibility of alternating minimization to local optima and its computational inefficiency in correspondence-free point set alignment. We propose a global optimization method based on support vectors derived from the convex hull vertices of permuted polygons. By proving a tight bound of $n(n-1)$ vertices, we resolve an open problem posed by Rote. Integrating the Procrustes-Wasserstein framework with a branch-and-bound algorithm, our approach achieves exact solutions in 2D and extends naturally to 3D. Evaluated on the MPEG-7 benchmark, the method requires only 12ms on average, achieving a 50-fold speedup over grid search while delivering superior accuracy. These improvements substantially enhance shape retrieval performance, demonstrating both theoretical rigor and practical efficiency for robust point set registration.