Accepted at CVPR 2019International audienceIn this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations. The proposed method obtains state-of-the-art performance on both the difficult Aachen Day-Ni...
Abstract. Current fine-grained classification approaches often rely on a robust localization of obje...
This is the accepted version of the paper to appear at Pattern Recognition Letters (PRL). The final ...
We present a novel deep architecture and a training strategy to learn a local feature pipeline from ...
Accepted at CVPR 2019International audienceIn this work we address the problem of finding reliable p...
In this work we address the problem of finding reliable pixel-level correspondences under difficult ...
International audienceWe tackle the problem of finding accurate and robust keypoint correspondences ...
Image matching is a central component in many computer vision applications. The field has progressed...
In recent years, convolutional networks have dramatically (re)emerged as the dominant paradigm for s...
This document presents a novel method based in Convolutional Neural Networks (CNN) to obtain corresp...
This thesis addresses the problem of investigating the properties and abilities of a variety of comp...
International audienceDeep learning has revolutionalized image-level tasks such as classification, b...
Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, ...
Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual fea...
One of the most important tasks of modern computer vision with a vast amount of applications is fi...
"Feature representations are the backbone of computer vision.They allow us to summarize the overwhel...
Abstract. Current fine-grained classification approaches often rely on a robust localization of obje...
This is the accepted version of the paper to appear at Pattern Recognition Letters (PRL). The final ...
We present a novel deep architecture and a training strategy to learn a local feature pipeline from ...
Accepted at CVPR 2019International audienceIn this work we address the problem of finding reliable p...
In this work we address the problem of finding reliable pixel-level correspondences under difficult ...
International audienceWe tackle the problem of finding accurate and robust keypoint correspondences ...
Image matching is a central component in many computer vision applications. The field has progressed...
In recent years, convolutional networks have dramatically (re)emerged as the dominant paradigm for s...
This document presents a novel method based in Convolutional Neural Networks (CNN) to obtain corresp...
This thesis addresses the problem of investigating the properties and abilities of a variety of comp...
International audienceDeep learning has revolutionalized image-level tasks such as classification, b...
Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, ...
Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual fea...
One of the most important tasks of modern computer vision with a vast amount of applications is fi...
"Feature representations are the backbone of computer vision.They allow us to summarize the overwhel...
Abstract. Current fine-grained classification approaches often rely on a robust localization of obje...
This is the accepted version of the paper to appear at Pattern Recognition Letters (PRL). The final ...
We present a novel deep architecture and a training strategy to learn a local feature pipeline from ...