PDE-based group equivariant convolutional neural networks

BMN Smets, J Portegies, EJ Bekkers… - Journal of Mathematical …, 2023 - Springer
We present a PDE-based framework that generalizes Group equivariant Convolutional
Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE …

Computing geodesic paths encoding a curvature prior for curvilinear structure tracking

D Chen, JM Mirebeau, M Shu… - Proceedings of the …, 2023 - National Acad Sciences
In this paper, we introduce an efficient method for computing curves minimizing a variant of
the Euler–Mumford elastica energy, with fixed endpoints and tangents at these endpoints …

[HTML][HTML] An aberration correction approach for single and dual aperture ultrasound imaging of the abdomen

VHJ Van Hal, JW Muller, MRHM Van Sambeek… - Ultrasonics, 2023 - Elsevier
Abdominal ultrasound image quality is hampered by phase aberration, that is mainly caused
by the large speed-of-sound (SoS) differences between fat and muscle tissue in the …

An elastica geodesic approach with convexity shape prior

D Chen, LD Cohen, JM Mirebeau… - Proceedings of the …, 2021 - openaccess.thecvf.com
The minimal geodesic models based on the Eikonal equations are capable of finding
suitable solutions in various image segmentation scenarios. Existing geodesic-based …

The stochastic simulation of karst conduit network structure using anisotropic fast marching, and its application to a geologically complex alpine karst system

C Fandel, F Miville, T Ferré, N Goldscheider… - Hydrogeology …, 2022 - Springer
Anisotropic fast-marching algorithms are computationally efficient tools for generating
realistic maps of karst conduit networks, constrained by both the spatial extent and the …

Integrating muscle fiber orientation from visible human data into radiotherapy target volumes

G Buti, A Ajdari, YL Chen, CP Bridge… - Physics in Medicine …, 2024 - iopscience.iop.org
Objective. A major challenge in treatment of tumors near skeletal muscle is defining the
target volume for suspected tumor invasion into the muscle. This study develops a …

A generalized asymmetric dual-front model for active contours and image segmentation

D Chen, J Spencer, JM Mirebeau… - … on Image Processing, 2021 - ieeexplore.ieee.org
The Voronoi diagram-based dual-front scheme is known as a powerful and efficient
technique for addressing the image segmentation and domain partitioning problems. In the …

A discontinuous Galerkin fast-sweeping eikonal solver for fast and accurate traveltime computation in 3D tilted anisotropic media

P Le Bouteiller, M Benjemaa, L Métivier, J Virieux - Geophysics, 2019 - library.seg.org
We tackle the challenging problem of efficient and accurate seismic traveltime computation
in 3D anisotropic media by applying the fast-sweeping method to a discontinuous Galerkin …

Geodesic models with convexity shape prior

D Chen, JM Mirebeau, M Shu, X Tai… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The minimal geodesic models established upon the eikonal equation framework are
capable of finding suitable solutions in various image segmentation scenarios. Existing …

FM2 Path Planner for UAV Applications with Curvature Constraints: A Comparative Analysis with Other Planning Approaches

S Garrido, J Muñoz, B López, F Quevedo, CA Monje… - Sensors, 2022 - mdpi.com
This paper studies the Fast Marching Square (FM 2) method as a competitive path planner
for UAV applications. The approach fulfills trajectory curvature constraints together with a …