Related papers: Online Learning of Correspondences between Images

Online Learning of Correspondences between Images

URL: http://arxiv.org/abs/2608.13104v1
Date: Thu, 13 Aug 2026 11:30:29 GMT
Title: Online Learning of Correspondences between Images
Abstract summary: We propose a novel method for learning of point correspondences between image sequences.<n>We derive such a method that optimize the mapping based on Neyman's chi-square divergence between the densities.<n>The resulting algorithm runs in real-time and is superior to state-of-the-art methods in terms of convergence and accuracy.
Score: 15.703640102714871
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: We propose a novel method for iterative learning of point correspondences between image sequences. Points moving on surfaces in 3D space are projected into two images. Given a point in either view, the considered problem is to determine the corresponding location in the other view. The geometry and distortions of the projections are unknown as is the shape of the surface. Given several pairs of point-sets but no access to the 3D scene, correspondence mappings can be found by excessive global optimization or by the fundamental matrix if a perspective projective model is assumed. However, an iterative solution on sequences of point-set pairs with general imaging geometry is preferable. We derive such a method that optimizes the mapping based on Neyman's chi-square divergence between the densities representing the uncertainties of the estimated and the actual locations. The densities are represented as channel vectors computed with a basis function approach. The mapping between these vectors is updated with each new pair of images such that fast convergence and high accuracy are achieved. The resulting algorithm runs in real-time and is superior to state-of-the-art methods in terms of convergence and accuracy in a number of experiments.

Related papers

SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry [69.89196162649091]
SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry) is a novel approach for estimating 3D geometry from extended monocular video sequences.<n>Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations.
arXiv Detail & Related papers (2026-06-19T10:23:25Z)
Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation [50.376243444909136]
We present a unified framework to predict both point-wise correspondences and shape between 3D shapes. We combine the deep functional map framework with classical surface deformation models to map shapes in both spectral and spatial domains.
arXiv Detail & Related papers (2024-02-29T07:26:23Z)
Neural Semantic Surface Maps [52.61017226479506]
We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement.
arXiv Detail & Related papers (2023-09-09T16:21:56Z)
Explicit Correspondence Matching for Generalizable Neural Radiance Fields [66.99907718824782]
We present a new NeRF method that is able to generalize to new unseen scenarios and perform novel view synthesis with as few as two source views.<n>The explicit correspondence matching is quantified with the cosine similarity between image features sampled at the 2D projections of a 3D point on different views.<n>Our method achieves state-of-the-art results on different evaluation settings, with the experiments showing a strong correlation between our learned cosine feature similarity and volume density.
arXiv Detail & Related papers (2023-04-24T17:46:01Z)
CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network [66.24726878647543]
Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet challenging task. Recent studies have shown the great potential of dense correspondence-based solutions. We propose a novel pose estimation algorithm named CheckerPose, which improves on three main aspects.
arXiv Detail & Related papers (2023-03-29T17:30:53Z)
Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation [31.968749056155467]
This paper proposes a simple, effective, and efficient topological loop closure detection pipeline with accurate 3-DoF metric pose estimation. We interpret the Cartesian birds' eye view (BEV) image projected from 3D LiDAR points as layered distribution of structures. A retrieval key is designed to accelerate the search of a database indexed by layered KD-trees.
arXiv Detail & Related papers (2023-02-13T07:18:24Z)
Rectifying homographies for stereo vision: analytical solution for minimal distortion [0.0]
Rectification is used to simplify the subsequent stereo correspondence problem. This work proposes a closed-form solution for the rectifying homographies that minimise perspective distortion.
arXiv Detail & Related papers (2022-02-28T22:35:47Z)
Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections [57.60094385551773]
We propose a trainable framework for learning a deformable 3D geometry model from inhomogeneous image collections. We in addition obtain the underlying 3D geometry of the objects depicted in the 2D images.
arXiv Detail & Related papers (2021-03-31T17:25:36Z)
Simplicial Complex based Point Correspondence between Images warped onto Manifolds [18.528929583956725]
We propose a constrained quadratic assignment problem (QAP) that matches each p-skeleton of the simplicial complexes. We significantly outperform existing state-of-the-art spherical matching methods on a diverse set of datasets.
arXiv Detail & Related papers (2020-07-05T16:41:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.