paper-with-me

Papers

Manifold Diffusion Fields

2023-05-24 · Ahmed A. Elhag, Yuyang Wang, Joshua M. Susskind, Miguel Angel Bautista

We present Manifold Diffusion Fields (MDF), an approach that unlocks learning of diffusion models of data in general non-Euclidean geometries. Leveraging insights from spectral geometry analysis, we define an intrinsic coordinate system on the manifold via the eigen-functions of the Laplace-Beltrami Operator. MDF represents functions using an explicit parametrization formed by a set of multiple input-output pairs. Our approach allows to sample continuous functions on manifolds and is invariant with respect to rigid and isometric transformations of the manifold. In addition, we show that MDF generalizes to the case where the training set contains functions on different manifolds. Empirical results on multiple datasets and manifolds including challenging scientific problems like weather prediction or molecular conformation show that MDF can capture distributions of such functions with better diversity and fidelity than previous approaches.

📄 PDF Abstract BibTeX arXiv:2305.15586

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Vector Diffusion Maps and the Connection Laplacian

2011-02-01 · Amit Singer, Hau-Tieng Wu

We introduce {\em vector diffusion maps} (VDM), a new mathematical framework for organizing and analyzing massive high dimensional data sets, images and shapes. VDM is a mathematical and algorithmic generalization of dif…

Dimensionality Reduction

A Geometric Insight into Equivariant Message Passing Neural Networks on Riemannian Manifolds

2023-10-16 · Ilyes Batatia

This work proposes a geometric insight into equivariant message passing on Riemannian manifolds. As previously proposed, numerical features on Riemannian manifolds are represented as coordinate-independent feature fields…

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

2023-10-11 · Jaehyeong Jo, Sung Ju Hwang

Learning the distribution of data on Riemannian manifolds is crucial for modeling data from non-Euclidean space, which is required by many applications in diverse scientific fields. Yet, existing generative models on man…

Denoising

Wrapped Gaussian Process Regression on Riemannian Manifolds

2018-06-01 · CVPR 2018 6 · Anton Mallasto, Aasa Feragen

Gaussian process (GP) regression is a powerful tool in non-parametric regression providing uncertainty estimates. However, it is limited to data in vector spaces. In fields such as shape analysis and diffusion tensor ima…

Gaussian Processesregression

Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds

2026-02-19 · Noah Trupin, Rahul Ghosh, Aadi Jangid arxiv

We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow gene…