Conference Paper

Une Méthode Plug-and-play pour le Recalage de Nuages de Points

Authors: Bouzeid Maurine, Bruel Pierre, Labsir Samy, Poulain Vincent, Tachella Julian, Tourneret Jean-Yves and Youssefi David

In Proc. XXXème Colloque Francophone de Traitement du Signal et des Images (GRETSI), Strasbourg, France, August 25-29, 2025.

Download document

Cet article présente une extension d’une approche plug-and-play pour le recalage de nuages de points 3D. Le problème de recalage de nuages de points 3D est formulé comme un problème inverse, et une approche plug-and-play est utilisée pour conjointement débruiter et recaler les nuages de points. Dans cet article, nous proposons d’optimiser la transformation de recalage en exploitant la structure de groupe de Lie de la transformation rigide SE(3). Des expériences menées sur des nuages de points LiDAR sont présentées mettant en évidence l’amélioration de la méthode par rapport à une méthode existante.

Read more

Signal and image processing / Earth observation

A Plug-and-play Approach for Point Cloud Registration

Authors: Bouzeid Maurine, Bruel Pierre, Poulain Vincent, Tachella Julian, Tourneret Jean-Yves and Youssefi David

In Proc. 23rd Statistical Signal Processing Workshop (SSP 2025), Edinburgh, Scotland, June 8-11, 2025.

Download document

Plug-and-play algorithms have shown impressive results on imaging inverse problems, such as registration, super-resolution, denoising and inpainting. These methods rely on a neural network denoiser to learn an implicit prior of the image to be estimated. This paper investigates a new plug-and-play approach for 3D point cloud registration, which is crucial for a wide range of applications such as urban planning, archaeology and autonomous vehicles. The 3D point cloud registration problem is formulated as an inverse problem whose unknowns are the image to be estimated and the transformation between the two point clouds. A plug-and-play approach using an alternating optimization strategy is proposed for solving the registration problem. Experiments conducted on synthetic data and Li-DAR point clouds are presented showing the potential of the method.

Read more

Signal and image processing / Earth observation