This is the accepted version of the paper to appear at Pattern Recognition Letters (PRL). The final journal version will be available at https://doi.org/10.1016/j.patrec.2023.08.012International audienceWe 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. Exper...
Image matching is a fundamental problem in computer vision. In the context of feature-based correspo...
In this paper, we propose an end-to-end framework that jointly learns keypoint detection, descriptor...
Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction...
This is the accepted version of the paper to appear at Pattern Recognition Letters (PRL). The final ...
International audienceWe present a novel learned keypoint detection method designed to maximize the ...
State-of-the-art keypoint detection algorithms have been designed to extract specific structures fro...
CVPR 2023; Source code available at https://verlab.dcc.ufmg.br/descriptors/dalf_cvpr23International ...
This document presents a novel method based in Convolutional Neural Networks (CNN) to obtain corresp...
Current best local descriptors are learned on a large data set of matching and non-matching keypoint...
none4noKeypoint detection represents the first stage in the majority of modern computer vision pipel...
International audienceWe tackle the problem of finding accurate and robust keypoint correspondences ...
This Thesis investigates using convolutional neural networks as a keypoint detector and descriptor f...
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feat...
none5noThe established approach to 3D keypoint detection consists in defining effective handcrafted ...
Image matching is a key component of many tasks in computer vision and its main objective is to find...
Image matching is a fundamental problem in computer vision. In the context of feature-based correspo...
In this paper, we propose an end-to-end framework that jointly learns keypoint detection, descriptor...
Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction...
This is the accepted version of the paper to appear at Pattern Recognition Letters (PRL). The final ...
International audienceWe present a novel learned keypoint detection method designed to maximize the ...
State-of-the-art keypoint detection algorithms have been designed to extract specific structures fro...
CVPR 2023; Source code available at https://verlab.dcc.ufmg.br/descriptors/dalf_cvpr23International ...
This document presents a novel method based in Convolutional Neural Networks (CNN) to obtain corresp...
Current best local descriptors are learned on a large data set of matching and non-matching keypoint...
none4noKeypoint detection represents the first stage in the majority of modern computer vision pipel...
International audienceWe tackle the problem of finding accurate and robust keypoint correspondences ...
This Thesis investigates using convolutional neural networks as a keypoint detector and descriptor f...
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feat...
none5noThe established approach to 3D keypoint detection consists in defining effective handcrafted ...
Image matching is a key component of many tasks in computer vision and its main objective is to find...
Image matching is a fundamental problem in computer vision. In the context of feature-based correspo...
In this paper, we propose an end-to-end framework that jointly learns keypoint detection, descriptor...
Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction...