Relational Epipolar Graphs for Robust Relative Camera Pose Estimation

• URL: http://arxiv.org/abs/2604.04554v1
• Date: Mon, 06 Apr 2026 09:29:37 GMT
• Title: Relational Epipolar Graphs for Robust Relative Camera Pose Estimation
• Abstract summary: A key component of Visual Simultaneous localization and Mapping (VSLAM) is estimating relative camera poses using matched keypoints.<n>In this work, we reformulate relative pose estimation as a relational inference problem over epipolar correspondence graphs.<n>Experiments on indoor and outdoor benchmarks show improved robustness to dense noise and large baseline variation compared to classical and learning-guided approaches.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A key component of Visual Simultaneous Localization and Mapping (VSLAM) is estimating relative camera poses using matched keypoints. Accurate estimation is challenged by noisy correspondences. Classical methods rely on stochastic hypothesis sampling and iterative estimation, while learning-based methods often lack explicit geometric structure. In this work, we reformulate relative pose estimation as a relational inference problem over epipolar correspondence graphs, where matched keypoints are nodes and nearby ones are connected by edges. Graph operations such as pruning, message passing, and pooling estimate a quaternion rotation, translation vector, and the Essential Matrix (EM). Minimizing a loss comprising (i) $\mathcal{L}_2$ differences with ground truth (GT), (ii) Frobenius norm between estimated and GT EMs, (iii) singular value differences, (iv) heading angle differences, and (v) scale differences, yields the relative pose between image pairs. The dense detector-free method LoFTR is used for matching. Experiments on indoor and outdoor benchmarks show improved robustness to dense noise and large baseline variation compared to classical and learning-guided approaches, highlighting the effectiveness of global relational consensus.

Related papers

• EpiDiffVO: Geometry-Aware Epipolar Diffusion for Robust Visual Odometry [0.0]
  Estimating relative pose from image pairs requires only a minimal subset of geometrically consistent correspondences.<n>We propose a sparse epipolar matching framework that predicts a compact set of correspondences optimized for geometric consistency.
  arXiv  Detail & Related papers  (2026-05-19T08:53:26Z)
• Mathematical Analysis of Image Matching Techniques [0.0]
  The study uses a manually constructed dataset of GPS-annotated satellite image tiles with intentional overlaps.<n>We examine the impact of the number of extracted keypoints on the resulting Inlier Ratio.
  arXiv  Detail & Related papers  (2026-04-08T20:24:40Z)
• Cosine-Normalized Attention for Hyperspectral Image Classification [7.170991480063844]
  Transformer-based methods have improved hyperspectral image classification (HSIC) by modeling long-range spatial-spectral dependencies.<n>This work revisits attention scoring from a geometric perspective and introduces a cosine-normalized attention formulation.<n> Experiments on three benchmark datasets demonstrate that the proposed approach consistently achieves higher performance.
  arXiv  Detail & Related papers  (2026-04-02T08:32:12Z)
• Differential pose optimization in descriptor space -- Combining Geometric and Photometric Methods for Motion Estimation [1.2977565963783035]
  Two-frame relative pose optimization is a fundamental problem in computer vision.<n>Two different kinds of error values are used: photometric error and re-projection error.<n>We investigate a third method that combines the strengths of both paradigms into a unified approach.
  arXiv  Detail & Related papers  (2026-02-15T20:13:29Z)
• LGU-SLAM: Learnable Gaussian Uncertainty Matching with Deformable Correlation Sampling for Deep Visual SLAM [11.715999663401591]
  Learnable 2D Gaussian uncertainty model is designed to associate matching-frame pairs. A multi-scale deformable correlation strategy is devised to adaptively fine-tune the sampling of each direction. Experiments on real-world and synthetic datasets are conducted to validate the effectiveness and superiority of our method.
  arXiv  Detail & Related papers  (2024-10-30T17:20:08Z)
• Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Prediction [22.894810893732416]
  The paper proposes a bidirectional correspondence prediction network with a point-wise attention-aware mechanism. Our key insight is that the correlations between each model point and scene point provide essential information for learning point-pair matches. Experimental results on the public datasets of LineMOD, YCB-Video, and Occ-LineMOD show that the proposed method achieves better performance than other state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-08-16T17:13:45Z)
• Learning Partial Correlation based Deep Visual Representation for Image Classification [61.0532370259644]
  We formulate sparse inverse covariance estimation (SICE) as a novel structured layer of CNN. Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem. Experiments show the efficacy and superior classification performance of our model.
  arXiv  Detail & Related papers  (2023-04-23T10:09:01Z)
• A Model for Multi-View Residual Covariances based on Perspective Deformation [88.21738020902411]
  We derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment.
  arXiv  Detail & Related papers  (2022-02-01T21:21:56Z)
• Learning Optical Flow from a Few Matches [67.83633948984954]
  We show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it. Experiments show that our method can reduce computational cost and memory use significantly, while maintaining high accuracy.
  arXiv  Detail & Related papers  (2021-04-05T21:44:00Z)
• Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints [80.60538408386016]
  Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry. We propose an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection.
  arXiv  Detail & Related papers  (2020-07-29T21:41:31Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency [103.22976097225457]
  We address weakly supervised semantic matching based on a deep network. We explicitly estimate the foreground regions to suppress the effect of background clutter. We develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent.
  arXiv  Detail & Related papers  (2020-03-31T22:38:09Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.