DiffusionNet: Discretization Agnostic Learning on Surfaces
| Autor: | Nicholas Sharp, Souhaib Attaiki, Keenan Crane, Maks Ovsjanikov |
|---|---|
| Přispěvatelé: | Carnegie Mellon University [Pittsburgh] (CMU), Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS), La Géometrie au Service du Numérique (GEOMERIX), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut Polytechnique de Paris (IP Paris), ANR-20-CHIA-0019,AIGRETTE,Analyse des Collections des Données Géométriques de Grande Taille(2020), European Project: 758800,ERC,ERC-2017-StG-758800,EXPROTEA(2018) |
| Rok vydání: | 2022 |
| Předmět: |
Computational Geometry (cs.CG)
FOS: Computer and information sciences Computer Science - Machine Learning geometric deep learning discrete differential geometry Computer Vision and Pattern Recognition (cs.CV) geometry processing partial differential equations Computer Science - Computer Vision and Pattern Recognition [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Computer Science - Computational Geometry Computer Graphics and Computer-Aided Design Machine Learning (cs.LG) |
| Zdroj: | ACM Transactions on Graphics ACM Transactions on Graphics, 2022, 41 (3), pp.1-16. ⟨10.1145/3507905⟩ Transactions on Graphics |
| ISSN: | 1557-7368 0730-0301 |
| DOI: | 10.1145/3507905 |
| Popis: | We introduce a new general-purpose approach to deep learning on 3D 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 which 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 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. Published in ACM Transactions on Graphics, presented at SIGGRAPH 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|