no code implementations • 13 Feb 2024 • Matthieu Vilain, Rémi Giraud, Hugo Germain, Guillaume Bourmaud
We then propose to limit the computation of the matching accuracy to textured regions, and show that in this case SAM often surpasses SDF methods.
no code implementations • 6 Apr 2022 • Coloma Ballester, Aurélie Bugeau, Hernan Carrillo, Michaël Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
In this chapter, we aim to study their influence on the results obtained by training a deep neural network, to answer the question: "Is it crucial to correctly choose the right color space in deep-learning based colorization?".
no code implementations • 6 Apr 2022 • Coloma Ballester, Aurélie Bugeau, Hernan Carrillo, Michaël Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
While learning to automatically colorize an image, one can define well-suited objective functions related to the desired color output.
no code implementations • 9 Nov 2020 • Luc Lafitte, Rémi Giraud, Cornel Zachiu, Mario Ries, Olivier Sutter, Antoine Petit, Olivier Seror, Clair Poignard, Baudouin Denis de Senneville
This can be achieved by the means of multi-modal deformable image registration (DIR), demonstrated to be capable of estimating dense and elastic deformations between images acquired by multiple imaging devices.
1 code implementation • 15 Apr 2020 • Rémi Giraud, Rodrigo Borba Pinheiro, Yannick Berthoumieu
Most of existing superpixel methods are designed to segment standard planar images as pre-processing for computer vision pipelines.
no code implementations • 9 Mar 2020 • Rémi Giraud, Yannick Berthoumieu
In this paper, we propose a new Nearest Neighbor-based Superpixel Clustering (NNSC) method to generate texture-aware superpixels in a limited computational time compared to previous approaches.
no code implementations • 9 Mar 2020 • Rémi Giraud, Merlin Boyer, Michaël Clément
A fast multi-scale non-local matching framework is also introduced for the search of similar descriptors at different resolution levels in an image dataset.
no code implementations • 20 Nov 2019 • Pierrick Coupé, Boris Mansencal, Michaël Clément, Rémi Giraud, Baudouin Denis de Senneville, Vinh-Thong Ta, Vincent Lepetit, José V. Manjon
Finally, we showed the interest of using semi-supervised learning to improve the performance of our method.
no code implementations • 5 Jun 2019 • Pierrick Coupé, Boris Mansencal, Michaël Clément, Rémi Giraud, Baudouin Denis de Senneville, Vinh-Thong Ta, Vincent Lepetit, José V. Manjon
Whole brain segmentation using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
Regular decompositions are necessary for most superpixel-based object recognition or tracking applications.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
To measure the regularity aspect, we propose a new global regularity measure (GR), which addresses the non-robustness of state-of-the-art metrics.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
During the decomposition, we propose to consider color features along the linear path between the pixel and the corresponding superpixel barycenter.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis, José V. Manjón, D. Louis Collins, Pierrick Coupé, Alzheimer's Disease Neuroimaging Initiative
On the EADC-ADNI dataset, we compare the hippocampal volumes obtained by manual and automatic segmentation.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis
Superpixels have become very popular in many computer vision applications.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
In this paper, we propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework.
no code implementations • 14 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
In this work, we propose a fast superpixel-based color transfer method (SCT) between two images.