Riemannian Denoising Diffusion Probabilistic Models
By: Zichen Liu , Wei Zhang , Christof Schütte and more
Potential Business Impact:
Creates realistic images from noisy data.
We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets of functions, including most of the manifolds relevant to applications. Existing methods for generative modeling on manifolds rely on substantial geometric information such as geodesic curves or eigenfunctions of the Laplace-Beltrami operator and, as a result, they are limited to manifolds where such information is available. In contrast, our method, built on a projection scheme, can be applied to more general manifolds, as it only requires being able to evaluate the value and the first order derivatives of the function that defines the submanifold. We provide a theoretical analysis of our method in the continuous-time limit, which elucidates the connection between our RDDPMs and score-based generative models on manifolds. The capability of our method is demonstrated on datasets from previous studies and on new datasets sampled from two high-dimensional manifolds, i.e. $\mathrm{SO}(10)$ and the configuration space of molecular system alanine dipeptide with fixed dihedral angle.
Similar Papers
Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models
CV and Pattern Recognition
Makes AI-generated pictures smoothly change.
Generative Learning of Densities on Manifolds
Machine Learning (CS)
Creates new realistic pictures from simple ideas.
Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
Machine Learning (CS)
Makes AI create realistic pictures faster.