Improving The Matching Of Deformable Objects By Learning To Detect Keypoints

Abstract

We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence. By leveraging true correspondences acquired by matching annotated image pairs with a specified descriptor extractor, we train an end-to-end convolutional neural network (CNN) to find keypoint locations that are more appropriate to the considered descriptor. For that, we apply geometric and photometric warpings to images to generate a supervisory signal, allowing the optimization of the detector. Experiments demonstrate that our method enhances the Mean Matching Accuracy of numerous descriptors when used in conjunction with our detection method, while outperforming the state-of-the-art keypoint detectors on real images of non-rigid objects by 20 p.p. We also apply our method on the complex real-world task of object retrieval where our detector performs on par with the finest keypoint detectors currently available for this task. The source code an

Stats

• citations5
• S2 citations—
• github stars8
• HF likes0
• heat score7.74
• arxiv keycadar2023improving

Related papers

• Enhancing Deformable Local Features By Jointly Learning To Detect And Describe Keypoints (2023)9.59
• End-to-end Learning Of Keypoint Detector And Descriptor For Pose Invariant 3D Matching (2018)12.40
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• KP-RED: Exploiting Semantic Keypoints For Joint 3D Shape Retrieval And Deformation (2024)8.35
• Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39
• Ur2kid: Unifying Retrieval, Keypoint Detection, And Keypoint Description Without Local Correspondence Supervision (2020)0.00
• Coe: Deep Coupled Embedding For Non-rigid Point Cloud Correspondences (2024)0.00
• Superncn: Neighbourhood Consensus Network For Robust Outdoor Scenes Matching (2019)2.26