DiffusionNet: Discretization Agnostic Learning on Surfaces - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue ACM Transactions on Graphics Année : 2022

DiffusionNet: Discretization Agnostic Learning on Surfaces

Résumé

We introduce a new general-purpose approach to deep learning on three-dimensional surfaces based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in resolution and sampling of a surface—a basic property that is crucial for practical applications. Our networks can be discretized on various geometric representations, such as triangle meshes or point clouds, and can even be trained on one representation and then applied to another. We optimize the spatial support of diffusion as a continuous network parameter ranging from purely local to totally global, removing the burden of manually choosing neighborhood sizes. The only other ingredients in the method are a multi-layer perceptron applied independently at each point and spatial gradient features to support directional filters. The resulting networks are simple, robust, and efficient. Here, we focus primarily on triangle mesh surfaces and demonstrate state-of-the-art results for a variety of tasks, including surface classification, segmentation, and non-rigid correspondence.
Fichier principal
Vignette du fichier
DiffusionNet_final_cmp.pdf (2.73 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03911881 , version 1 (23-12-2022)

Identifiants

Citer

Nicholas Sharp, Souhaib Attaiki, Keenan Crane, Maks Ovsjanikov. DiffusionNet: Discretization Agnostic Learning on Surfaces. ACM Transactions on Graphics, 2022, 41 (3), pp.1-16. ⟨10.1145/3507905⟩. ⟨hal-03911881⟩
97 Consultations
87 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More