Improving the matching of deformable objects by learning to detect keypoints - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2023

Improving the matching of deformable objects by learning to detect keypoints

Résumé

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 and trained models are publicly available at https://github.com/verlab/LearningToDetect_PRL_2023

Dates et versions

hal-04195849 , version 1 (04-09-2023)

Licence

Paternité

Identifiants

Citer

Felipe Cadar, Welerson Melo, Vaishnavi Kanagasabapathi, Guilherme Potje, Renato Martins, et al.. Improving the matching of deformable objects by learning to detect keypoints. Pattern Recognition Letters, 2023, ⟨10.1016/j.patrec.2023.08.012⟩. ⟨hal-04195849⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More