Search Results for author:
Found 16 papers, 1 papers with code
Are Semi-Dense Detector-Free Methods Good at Matching Local Features?
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.
Influence of Color Spaces for Deep Learning Image Colorization
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?".
Analysis of Different Losses for Deep Learning Image Colorization
While learning to automatically colorize an image, one can define well-suited objective functions related to the desired color output.
Patch-based field-of-view matching in multi-modal images for electroporation-based ablations
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.
Generalized Shortest Path-based Superpixels for Accurate Segmentation of Spherical Images
Most of existing superpixel methods are designed to segment standard planar images as pre-processing for computer vision pipelines.
Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
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.
Multi-Scale Superpatch Matching using Dual Superpixel Descriptors
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.
AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation
Finally, we showed the interest of using semi-supervised learning to improve the performance of our method.
AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation
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.
Robust Shape Regularity Criteria for Superpixel Evaluation
Regular decompositions are necessary for most superpixel-based object recognition or tracking applications.
Evaluation Framework of Superpixel Methods with a Global Regularity Measure
To measure the regularity aspect, we propose a new global regularity measure (GR), which addresses the non-robustness of state-of-the-art metrics.
Robust superpixels using color and contour features along linear path
During the decomposition, we propose to consider color features along the linear path between the pixel and the corresponding superpixel barycenter.
An Optimized PatchMatch for Multi-scale and Multi-feature Label Fusion
On the EADC-ADNI dataset, we compare the hippocampal volumes obtained by manual and automatic segmentation.
SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches
Superpixels have become very popular in many computer vision applications.
SCALP: Superpixels with Contour Adherence using Linear Path
In this paper, we propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework.
Superpixel-based Color Transfer
In this work, we propose a fast superpixel-based color transfer method (SCT) between two images.
