Geometry-Informed Neural Networks
- URL: http://arxiv.org/abs/2402.14009v2
- Date: Mon, 27 May 2024 16:12:14 GMT
- Title: Geometry-Informed Neural Networks
- Authors: Arturs Berzins, Andreas Radler, Sebastian Sanokowski, Sepp Hochreiter, Johannes Brandstetter,
- Abstract summary: We introduce geometry-informed neural networks (GINNs) to train shape generative models.
GINNs combine (i) learning under constraints, (ii) neural fields as a suitable representation, and (iii) generating diverse solutions to under-determined problems.
- Score: 16.03834563833674
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Geometry is a ubiquitous language of computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learning methods and motivates the exploration of alternative learning strategies. To this end, we introduce geometry-informed neural networks (GINNs) to train shape generative models \emph{without any data}. GINNs combine (i) learning under constraints, (ii) neural fields as a suitable representation, and (iii) generating diverse solutions to under-determined problems. We apply GINNs to several two and three-dimensional problems of increasing levels of complexity. Our results demonstrate the feasibility of training shape generative models in a data-free setting. This new paradigm opens several exciting research directions, expanding the application of generative models into domains where data is sparse.
Related papers
- Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations [13.208548352092455]
For partial differential equations on domains of arbitrary shapes, existing works of neural operators attempt to learn a mapping from geometries to solutions.
We propose reference neural operators (RNO) to learn the smooth dependence of solutions on geometric deformations.
RNO outperforms baseline models in accuracy by a large lead and achieves up to 80% error reduction.
arXiv Detail & Related papers (2024-05-27T06:50:17Z) - A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes [49.32130498861987]
We study the case of non-differentiable activation functions, such as ReLU.
Two recent works introduced a geometric framework to study neural networks.
We illustrate our findings with some numerical experiments on classification of images and thermodynamic problems.
arXiv Detail & Related papers (2024-04-09T08:11:46Z) - A Survey of Geometric Graph Neural Networks: Data Structures, Models and
Applications [67.33002207179923]
This paper presents a survey of data structures, models, and applications related to geometric GNNs.
We provide a unified view of existing models from the geometric message passing perspective.
We also summarize the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
arXiv Detail & Related papers (2024-03-01T12:13:04Z) - GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis [25.594334301684903]
We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes.
Key ingredient of our method is a neural skeleton-based representation encoding information on both shape topology and geometry.
We demonstrate significantly more faithful surface reconstruction and diverse shape generation results compared to the state-of-the-art.
arXiv Detail & Related papers (2024-02-26T20:00:57Z) - Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences.
It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations.
Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
arXiv Detail & Related papers (2024-02-20T15:23:24Z) - MMGP: a Mesh Morphing Gaussian Process-based machine learning method for
regression of physical problems under non-parameterized geometrical
variability [0.30693357740321775]
We propose a machine learning method that do not rely on graph neural networks.
The proposed methodology can easily deal with large meshes without the need for explicit shape parameterization.
arXiv Detail & Related papers (2023-05-22T09:50:15Z) - Neural Template: Topology-aware Reconstruction and Disentangled
Generation of 3D Meshes [52.038346313823524]
This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology.
Our method is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.
arXiv Detail & Related papers (2022-06-10T08:32:57Z) - Self-Supervised Graph Representation Learning for Neuronal Morphologies [75.38832711445421]
We present GraphDINO, a data-driven approach to learn low-dimensional representations of 3D neuronal morphologies from unlabeled datasets.
We show, in two different species and across multiple brain areas, that this method yields morphological cell type clusterings on par with manual feature-based classification by experts.
Our method could potentially enable data-driven discovery of novel morphological features and cell types in large-scale datasets.
arXiv Detail & Related papers (2021-12-23T12:17:47Z) - Scalable Surface Reconstruction with Delaunay-Graph Neural Networks [14.128976778330474]
We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds.
Our approach can cope with the scale and variety of point cloud defects encountered in real-life Multi-View Stereo (MVS) acquisitions.
arXiv Detail & Related papers (2021-07-13T14:30:32Z) - E(n) Equivariant Graph Neural Networks [86.75170631724548]
This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs)
In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance.
arXiv Detail & Related papers (2021-02-19T10:25:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.