English
Related papers

Related papers: Minimising Willmore Energy via Neural Flow

200 papers

We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. ShapeFlow allows learning a multi-template deformation space that is agnostic to shape topology,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-25 Chiyu "Max" Jiang , Jingwei Huang , Andrea Tagliasacchi , Leonidas Guibas

A new approach is proposed for study structure and properties of the total squared mean curvature $W$ of surfaces in ${\bf R}^3$. It is based on the generalized Weierstrass formulae for inducing surfaces. The quantity $W$ (Willmore…

dg-ga · Mathematics 2008-02-03 B. G. Konopelchenko , I. A. Taimanov

Various topological techniques and tools have been applied to neural networks in terms of network complexity, explainability, and performance. One fundamental assumption of this line of research is the existence of a global (Euclidean)…

Machine Learning · Computer Science 2022-01-02 Dongfang Zhao

Engineers learn from every design they create, building intuition that helps them quickly identify promising solutions for new problems. Topology optimization (TO) - a well-established computational method for designing structures with…

Computational Engineering, Finance, and Science · Computer Science 2025-02-05 Igor Kuszczak , Gawel Kus , Federico Bosi , Miguel A. Bessa

The prohibitive cost and low fidelity of experimental data in industry scale thermofluid systems limit the usefulness of pure data-driven machine learning methods. Physics-informed neural networks (PINN) strive to overcome this by embedding…

Fluid Dynamics · Physics 2021-05-25 Ryno Laubscher , Pieter Rousseau

Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between…

Machine Learning · Statistics 2019-02-25 Felix Draxler , Kambis Veschgini , Manfred Salmhofer , Fred A. Hamprecht

Neural networks are widely used for image-related tasks but typically demand considerable computing power. Once a network has been trained, however, its memory- and compute-footprint can be reduced by compression. In this work, we focus on…

Machine Learning · Computer Science 2025-11-13 Alper Kalle , Theo Rudkiewicz , Mohamed-Oumar Ouerfelli , Mohamed Tamaazousti

To learn about basic aspects of nano-scale spherical molecular shells during their formation, spherically curved two-dimensional N-particle Lennard-Jones systems are simulated, studying curvature evolution paths at zero-temperature. For…

Atomic and Molecular Clusters · Physics 2009-11-11 J. M. Voogd , P. M. A. Sloot , R. van Dantzig

For every two-dimensional torus $T^2$ and every $k\in \mathbb{N}$, $k\ge 3$, we construct a conformal Willmore immersion $f:T^2\to \mathbb{R}^4$ with exactly one point of density $k$ and Willmore energy $4\pi k$. Moreover, we show that the…

Differential Geometry · Mathematics 2015-10-26 Tobias Lamm , Reiner M. Schätzle

The present work investigates the use of physics-informed neural networks (PINNs) for the 3D reconstruction of unsteady gravity currents from limited data. In the PINN context, the flow fields are reconstructed by training a neural network…

Fluid Dynamics · Physics 2023-06-16 Mickaël Delcey , Yoann Cheny , Sébastien Kiesgen de Richter

We introduce a flow of maps from a compact surface of arbitrary genus to an arbitrary Riemannian manifold which has elements in common with both the harmonic map flow and the mean curvature flow, but is more effective at finding minimal…

Differential Geometry · Mathematics 2016-05-18 Melanie Rupflin , Peter M. Topping

Recent advances in the application of physics-informed learning into the field of fluid mechanics have been predominantly grounded in the Newtonian framework, primarly leveraging Navier-Stokes Equation or one of its various derivative to…

Fluid Dynamics · Physics 2024-04-25 Hussam Alhussein , Mohammed Daqaq

We study the compactness of Willmore surfaces without assuming the convergence of the induced complex structures. In particular, we compute the energy loss in the neck in terms of the residue and we prove that the limit of the image of the…

Differential Geometry · Mathematics 2024-11-12 Yuxiang Li , Hao Yin , Jie Zhou

The evolution of a closed two-dimensional surface driven by both mean curvature flow and a reaction--diffusion process on the surface is formulated into a system, which couples the velocity law not only to the surface partial differential…

Numerical Analysis · Mathematics 2020-08-18 Balázs Kovács , Buyang Li , Christian Lubich

We use the inverse mean curvature flow with a free boundary perpendicular to the sphere to prove a geometric inequality involving the Willmore energy for convex hypersurfaces of dimension $n\geq 3$ with boundary on the sphere.

Differential Geometry · Mathematics 2017-06-27 Ben Lambert , Julian Scheuer

Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes limitations on data distributions that reside on…

Computer Vision and Pattern Recognition · Computer Science 2022-08-19 Janis Postels , Martin Danelljan , Luc Van Gool , Federico Tombari

We present our progress on the application of physics informed deep learning to reservoir simulation problems. The model is a neural network that is jointly trained to respect governing physical laws and match boundary conditions. The…

Fluid Dynamics · Physics 2021-04-26 Cedric Fraces Gasmi , Hamdi Tchelepi

In this article we are interested in the microscopic modeling of a two-dimensional two-well problem which arises from the square-to-rectangular transformation in (two-dimensional) shape-memory materials. In this discrete set-up, we focus on…

Analysis of PDEs · Mathematics 2015-09-29 Georgy Kitavtsev , Stephan Luckhaus , Angkana Rüland

We consider minimization problems of functionals given by the difference between the Willmore functional of a closed surface and its area, when the latter is multiplied by a positive constant weight $\Lambda$ and when the surfaces are…

Analysis of PDEs · Mathematics 2023-12-12 Marco Pozzetta

Learning a graph topology to reveal the underlying relationship between data entities plays an important role in various machine learning and data analysis tasks. Under the assumption that structured data vary smoothly over a graph, the…

Machine Learning · Statistics 2023-08-23 Xingyue Pu , Tianyue Cao , Xiaoyun Zhang , Xiaowen Dong , Siheng Chen