arXiv subjects

Théo Bertrand

Publications and source records attributed to Théo Bertrand.

3 recordsLinked to original sources

arXiv2025

Dynamic off-the-grid untangling of curves by Riemannian metric

We propose an improved strategy for point sources tracking in a temporal stack through an off-the-grid fashion, inspired by the Benamou-Brenier regularisation in the literature. We define a lifting of the problem in the higher-dimensional space of the roto-translation group. This allows us to overcome the theoretical limitation of the off-the-grid method towards tangled point source trajectories, thus enabling the reconstruction and untangling even from the numerical standpoint. We define accordingly a new regularisation based on the relaxed Reeds-Shepp metric, an approximation of the sub-Riemannian Reeds-Shepp metric, further allowing control on the local curvature of the recovered trajectories. Then, we derive some properties of the discretisation and prove a $Γ$-convergence result, fostering interest for practical applications of polygonal, Bézier, and piecewise geodesic discretisation. We finally test our proposed method on a localisation problem example, and give a fair comparison with the state-of-the-art off-the-grid method.

math.DG↗

arXiv2023

Fitting tree model with CNN and geodesics to track vesselsand application to Ultrasound Localization Microscopy data

Segmentation of tubular structures in vascular imaging is a well studied task, although it is rare that we try to infuse knowledge of the tree-like structure of the regions to be detected. Our work focuses on detecting the important landmarks in the vascular network (via CNN performing both localization and classification of the points of interest) and representing vessels as the edges in some minimal distance tree graph. We leverage geodesic methods relevant to the detection of vessels and their geometry, making use of the space of positions and orientations so that 2D vessels can be accurately represented as trees. We build our model to carry tracking on Ultrasound Localization Microscopy (ULM) data, proposing to build a good cost function for tracking on this type of data. We also test our framework on synthetic and eye fundus data. Results show that scarcity of well annotated ULM data is an obstacle to localization of vascular landmarks but the Orientation Score built from ULM data yields good geodesics for tracking blood vessels.

cs.CV↗

arXiv2023

Fast Marching Energy CNN

Leveraging geodesic distances and the geometrical information they convey is key for many data-oriented applications in imaging. Geodesic distance computation has been used for long for image segmentation using Image based metrics. We introduce a new method by generating isotropic Riemannian metrics adapted to a problem using CNN and give as illustrations an example of application. We then apply this idea to the segmentation of brain tumours as unit balls for the geodesic distance computed with the metric potential output by a CNN, thus imposing geometrical and topological constraints on the output mask. We show that geodesic distance modules work well in machine learning frameworks and can be used to achieve state-of-the-art performances while ensuring geometrical and/or topological properties.

cs.CV↗