The goal of this thesis is to develop methods for establishing correspondences between pairs of images in challenging situations, such as extreme illumination changes, scenes with little texture or with repetitive structures, and matching parts of objects which belong to the same class, but which may have large intra-class appearance differences. In summary, our contributions are the following: (i) we develop a trainable approach for parametric image alignment by means of a siamese network model, (ii) we devise a weakly-supervised training approach, which allow training from real image pairs having only annotation at the level of image-pairs, (iii) we propose the Neighbourhood Consensus Networks which can be used to robustly estimate corres...
We propose a novel method for iterative learning of point correspondences between image sequences. P...
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark det...
We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes...
L’objectif de cette thèse est de développer des méthodes pour la mise en correspondance entre de pai...
We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given...
International audienceIn this work we target the problem of estimating accurately localised correspo...
Abstract Finding matching images across large datasets plays a key role in many computer vision app...
We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In ...
Seeing allows animals and people alike to gather information from a distance, often with high spatia...
Cette thèse propose un système d’appariement de formes dans les images. La plupart des systèmes déve...
This thesis addresses the task of establishing adense correspondence between an image and a 3Dobject...
We explore the training of deep neural networks to produce vector representations using weakly label...
This work aims at defining an extension of a competitive method for matching correspondences in ste...
The objective of this thesis is to explore the use of graph matching in object recognition systems. ...
Even though the prospect of fusing images issued by different medical imagery systems is highly cont...
We propose a novel method for iterative learning of point correspondences between image sequences. P...
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark det...
We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes...
L’objectif de cette thèse est de développer des méthodes pour la mise en correspondance entre de pai...
We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given...
International audienceIn this work we target the problem of estimating accurately localised correspo...
Abstract Finding matching images across large datasets plays a key role in many computer vision app...
We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In ...
Seeing allows animals and people alike to gather information from a distance, often with high spatia...
Cette thèse propose un système d’appariement de formes dans les images. La plupart des systèmes déve...
This thesis addresses the task of establishing adense correspondence between an image and a 3Dobject...
We explore the training of deep neural networks to produce vector representations using weakly label...
This work aims at defining an extension of a competitive method for matching correspondences in ste...
The objective of this thesis is to explore the use of graph matching in object recognition systems. ...
Even though the prospect of fusing images issued by different medical imagery systems is highly cont...
We propose a novel method for iterative learning of point correspondences between image sequences. P...
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark det...
We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes...