FPC-Net: Revisiting SuperPoint with Descriptor-Free Keypoint Detection via Feature Pyramids and Consistency-Based Implicit Matching

• URL: http://arxiv.org/abs/2507.10770v1
• Date: Mon, 14 Jul 2025 19:52:24 GMT
• Title: FPC-Net: Revisiting SuperPoint with Descriptor-Free Keypoint Detection via Feature Pyramids and Consistency-Based Implicit Matching
• Authors: Ionuţ Grigore, Călin-Adrian Popa, Claudiu Leoveanu-Condrei,
• Abstract summary: This work introduces a technique where interest points are inherently associated during detection, eliminating the need for computing, storing, transmitting, or matching descriptors.<n>Although the matching accuracy is marginally lower than that of conventional approaches, our method completely eliminates the need for descriptors.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The extraction and matching of interest points are fundamental to many geometric computer vision tasks. Traditionally, matching is performed by assigning descriptors to interest points and identifying correspondences based on descriptor similarity. This work introduces a technique where interest points are inherently associated during detection, eliminating the need for computing, storing, transmitting, or matching descriptors. Although the matching accuracy is marginally lower than that of conventional approaches, our method completely eliminates the need for descriptors, leading to a drastic reduction in memory usage for localization systems. We assess its effectiveness by comparing it against both classical handcrafted methods and modern learned approaches.

Related papers

• MatChA: Cross-Algorithm Matching with Feature Augmentation [5.314522402001238]
  State-of-the-art methods fail to solve visual localization in scenarios where different devices use different sparse feature extraction algorithms.<n>We show that our method significantly improves image matching and visual localization in the cross-feature scenario.
  arXiv  Detail & Related papers  (2025-06-27T15:43:51Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes.<n>Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes.<n>We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• Generalized Correspondence Matching via Flexible Hierarchical Refinement and Patch Descriptor Distillation [13.802788788420175]
  Correspondence matching plays a crucial role in numerous robotics applications. This paper addresses the limitations of deep feature matching (DFM), a state-of-the-art (SoTA) plug-and-play correspondence matching approach. Our proposed method achieves an overall performance in terms of mean matching accuracy of 0.68, 0.92, and 0.95 with respect to the tolerances of 1, 3, and 5 pixels, respectively.
  arXiv  Detail & Related papers  (2024-03-08T15:32:18Z)
• 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)
• ResMatch: Residual Attention Learning for Local Feature Matching [51.07496081296863]
  We rethink cross- and self-attention from the viewpoint of traditional feature matching and filtering. We inject the similarity of descriptors and relative positions into cross- and self-attention score. We mine intra- and inter-neighbors according to the similarity of descriptors and relative positions.
  arXiv  Detail & Related papers  (2023-07-11T11:32:12Z)
• Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network [52.29330138835208]
  Accurately matching local features between a pair of images is a challenging computer vision task. Previous studies typically use attention based graph neural networks (GNNs) with fully-connected graphs over keypoints within/across images. We propose MaKeGNN, a sparse attention-based GNN architecture which bypasses non-repeatable keypoints and leverages matchable ones to guide message passing.
  arXiv  Detail & Related papers  (2023-07-04T02:50:44Z)
• A Coarse-to-Fine Place Recognition Approach using Attention-guided Descriptors and Overlap Estimation [13.018093610656507]
  We present a novel coarse-to-fine approach to place recognition. In the coarse stage, our approach utilizes an attention-guided network to generate attention-guided descriptors. We then employ a fast affinity-based candidate selection process to identify the Top-K most similar candidates. In the fine stage, we estimate pairwise overlap among the narrowed-down place candidates to determine the final match.
  arXiv  Detail & Related papers  (2023-03-13T05:56:36Z)
• ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization [71.91942002659795]
  We investigate and adapt network quantization techniques to accelerate inference and enable its use on compute limited platforms. ZippyPoint, our efficient quantized network with binary descriptors, improves the network runtime speed, the descriptor matching speed, and the 3D model size. These improvements come at a minor performance degradation as evaluated on the tasks of homography estimation, visual localization, and map-free visual relocalization.
  arXiv  Detail & Related papers  (2022-03-07T18:59:03Z)
• Recall@k Surrogate Loss with Large Batches and Similarity Mixup [62.67458021725227]
  Direct optimization, by gradient descent, of an evaluation metric is not possible when it is non-differentiable. In this work, a differentiable surrogate loss for the recall is proposed. The proposed method achieves state-of-the-art results in several image retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T11:09:11Z)
• 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.