Geodesic squared exponential kernel for non-rigid shape registration - 3IA Côte d’Azur – Interdisciplinary Institute for Artificial Intelligence Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Geodesic squared exponential kernel for non-rigid shape registration

Résumé

This work addresses the problem of non-rigid registration of 3D scans, which is at the core of shape modeling techniques. Firstly, we propose a new kernel based on geodesic distances for the Gaussian Process Morphable Models (GPMMs) framework. The use of geodesic distances into the kernel makes it more adapted to the topological and geometric characteristics of the surface and leads to more realistic deformations around holes and curved areas. Since the kernel possesses hyperparameters we have optimized them for the task of face registration on the FaceWarehouse dataset. We show that the Geodesic squared exponential kernel performs significantly better than state of the art kernels for the task of face registration on all the 20 expressions of the FaceWarehouse dataset. Secondly, we propose a modification of the loss function used in the non-rigid ICP registration algorithm, that allows to weight the correspondences according to the confidence given to them. As a use case, we show that we can make the registration more robust to outliers in the 3D scans, such as non-skin parts.
Fichier principal
Vignette du fichier
sample_FG2021.pdf (16.71 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03500440 , version 1 (22-12-2021)

Identifiants

Citer

Florent Jousse, Xavier Pennec, Hervé Delingette, Matilde Gonzalez. Geodesic squared exponential kernel for non-rigid shape registration. FG 2021 - IEEE International Conference on Automatic Face and Gesture Recognition, Dec 2021, JODHPUR, India. ⟨10.1109/FG52635.2021.9666997⟩. ⟨hal-03500440⟩
41 Consultations
58 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More