XRefine: Attention-Guided Keypoint Match Refinement

• URL: http://arxiv.org/abs/2601.12530v1
• Date: Sun, 18 Jan 2026 18:32:53 GMT
• Title: XRefine: Attention-Guided Keypoint Match Refinement
• Authors: Jan Fabian Schmid, Annika Hagemann,
• Abstract summary: XRefine is a novel, detector-agnostic approach for sub-pixel keypoint refinement.<n>Our cross-attention-based architecture learns to predict refined keypoint coordinates without relying on internal detector representations.<n>Experiments on MegaDepth, KITTI, and ScanNet demonstrate that the approach consistently improves geometric estimation accuracy.
• Score: 2.318985488473778
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse keypoint matching is crucial for 3D vision tasks, yet current keypoint detectors often produce spatially inaccurate matches. Existing refinement methods mitigate this issue through alignment of matched keypoint locations, but they are typically detector-specific, requiring retraining for each keypoint detector. We introduce XRefine, a novel, detector-agnostic approach for sub-pixel keypoint refinement that operates solely on image patches centered at matched keypoints. Our cross-attention-based architecture learns to predict refined keypoint coordinates without relying on internal detector representations, enabling generalization across detectors. Furthermore, XRefine can be extended to handle multi-view feature tracks. Experiments on MegaDepth, KITTI, and ScanNet demonstrate that the approach consistently improves geometric estimation accuracy, achieving superior performance compared to existing refinement methods while maintaining runtime efficiency. Our code and trained models can be found at https://github.com/boschresearch/xrefine.

Related papers

• From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection [23.384541298514574]
  Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM.<n>We introduce TraqPoint, a novel, end-to-end Reinforcement Learning framework designed to optimize keypoints directly on image sequences.<n>Our core innovation is a track-aware reward mechanism that jointly encourages the consistency and distinctiveness of keypoints across multiple views.
  arXiv  Detail & Related papers  (2026-02-24T07:24:25Z)
• RaCo: Ranking and Covariance for Practical Learned Keypoints [51.38393049306958]
  RaCo is designed to learn robust and versatile keypoints suitable for a variety of 3D computer vision tasks.<n>RaCo operates without the need for covisible image pairs.
  arXiv  Detail & Related papers  (2026-02-17T17:39:52Z)
• Learning to Make Keypoints Sub-Pixel Accurate [80.55676599677824]
  This work addresses the challenge of sub-pixel accuracy in detecting 2D local features. We propose a novel network that enhances any detector with sub-pixel precision by learning an offset vector for detected features.
  arXiv  Detail & Related papers  (2024-07-16T12:39:56Z)
• Deep Homography Estimation for Visual Place Recognition [49.235432979736395]
  We propose a transformer-based deep homography estimation (DHE) network. It takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Experiments on benchmark datasets show that our method can outperform several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-25T13:22:17Z)
• Improving the matching of deformable objects by learning to detect keypoints [6.4587163310833855]
  We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence. We train an end-to-end convolutional neural network (CNN) to find keypoint locations that are more appropriate to the considered descriptor. Experiments demonstrate that our method enhances the Mean Matching Accuracy of numerous descriptors when used in conjunction with our detection method. We also apply our method on the complex real-world task object retrieval where our detector performs on par with the finest keypoint detectors currently available for this task.
  arXiv  Detail & Related papers  (2023-09-01T13:02:19Z)
• DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching [14.837075102089]
  Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Previous learning-based methods typically learn descriptors with keypoints, and treat the keypoint detection as a binary classification task on mutual nearest neighbours. In this work, we learn keypoints directly from 3D consistency. To this end, we derive a semi-supervised two-view detection objective to expand this set to a desired number of detections. Results show that our approach, DeDoDe, achieves significant gains on multiple geometry benchmarks.
  arXiv  Detail & Related papers  (2023-08-16T16:37:02Z)
• KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration [28.96448680048584]
  KeyPoint Positioning System (KeyPosS) is first framework to deduce exact landmark coordinates by triangulating distances between points of interest and anchor points predicted by a fully convolutional network. Experiments on four datasets demonstrate state-of-the-art performance, with KeyPosS outperforming existing methods in low-resolution settings despite minimal computational overhead.
  arXiv  Detail & Related papers  (2023-05-25T19:30:21Z)
• Pixel-Perfect Structure-from-Motion with Featuremetric Refinement [96.73365545609191]
  We refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views. This significantly improves the accuracy of camera poses and scene geometry for a wide range of keypoint detectors. Our system easily scales to large image collections, enabling pixel-perfect crowd-sourced localization at scale.
  arXiv  Detail & Related papers  (2021-08-18T17:58:55Z)
• Soft Expectation and Deep Maximization for Image Feature Detection [68.8204255655161]
  We propose SEDM, an iterative semi-supervised learning process that flips the question and first looks for repeatable 3D points, then trains a detector to localize them in image space. Our results show that this new model trained using SEDM is able to better localize the underlying 3D points in a scene.
  arXiv  Detail & Related papers  (2021-04-21T00:35:32Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)
• 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)

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.