Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models

• URL: http://arxiv.org/abs/2510.05509v1
• Date: Tue, 07 Oct 2025 01:54:47 GMT
• Title: Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models
• Authors: Shinnosuke Saito, Takashi Matsubara,
• Abstract summary: Diffusion models are powerful deep generative models (DGMs) that generate high-fidelity, diverse content.<n>Unlike classical DGMs, they lack an explicit, tractable low-dimensional latent space that parameterizes the data manifold.<n>We propose a novel metric on the noise space, inspired by recent findings that the Jacobian of the score function captures the tangent spaces to the local data manifold.
• Score: 13.063093054280946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models are powerful deep generative models (DGMs) that generate high-fidelity, diverse content. However, unlike classical DGMs, they lack an explicit, tractable low-dimensional latent space that parameterizes the data manifold. This absence limits manifold-aware analysis and operations, such as interpolation and editing. Existing interpolation methods for diffusion models typically follow paths through high-density regions, which are not necessarily aligned with the data manifold and can yield perceptually unnatural transitions. To exploit the data manifold learned by diffusion models, we propose a novel Riemannian metric on the noise space, inspired by recent findings that the Jacobian of the score function captures the tangent spaces to the local data manifold. This metric encourages geodesics in the noise space to stay within or run parallel to the learned data manifold. Experiments on image interpolation show that our metric produces perceptually more natural and faithful transitions than existing density-based and naive baselines.

Related papers

• What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold [0.053713376045563095]
  We introduce a score-based Riemannian metric to characterize the intrinsic geometry of a data manifold.<n>Our approach creates a geometry where geodesics naturally follow the manifold's contours.<n>We show that our score-based geodesics capture meaningful perpendicular transformations that respect the underlying data distribution.
  arXiv  Detail & Related papers  (2025-05-16T11:19:57Z)
• Riemannian Denoising Diffusion Probabilistic Models [7.964790563398277]
  We propose RDDPMs for learning distributions on submanifolds of Euclidean space that are level sets of functions.<n>We provide a theoretical analysis of our method in the continuous-time limit.<n>The capability of our method is demonstrated on datasets from previous studies and on new sampled datasets.
  arXiv  Detail & Related papers  (2025-05-07T11:37:16Z)
• Image Interpolation with Score-based Riemannian Metrics of Diffusion Models [9.514940899499752]
  This paper introduces a novel framework that treats the data space of pre-trained diffusion models as a Riemannian manifold.<n> Experiments with MNIST and Stable Diffusion show that this geometry-aware approach yields images that are more realistic, less noisy, and more faithful to prompts than existing methods.
  arXiv  Detail & Related papers  (2025-04-28T22:04:20Z)
• Continuous Diffusion Model for Language Modeling [64.7425225935854]
  Existing continuous diffusion models for discrete data underperform compared to discrete methods.<n>We propose a continuous diffusion model for language modeling that incorporates the geometry of the underlying categorical distribution.<n>Our method outperforms existing discrete diffusion models and approaches the performance of autoregressive models.
  arXiv  Detail & Related papers  (2025-02-17T08:54:29Z)
• Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions [6.9408143976091745]
  Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions.<n>We study DDPMs under the manifold hypothesis and prove that they achieve rates independent of the ambient dimension in terms of score learning.<n>In terms of sampling complexity, we obtain rates independent of the ambient dimension w.r.t. the Kullback-Leibler divergence, and $O(sqrtD)$ w.r.t. the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-09-27T14:57:18Z)
• Scaling Riemannian Diffusion Models [68.52820280448991]
  We show that our method enables us to scale to high dimensional tasks on nontrivial manifold. We model QCD densities on $SU(n)$ lattices and contrastively learned embeddings on high dimensional hyperspheres.
  arXiv  Detail & Related papers  (2023-10-30T21:27:53Z)
• Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes [57.396578974401734]
  We introduce a principled framework for building a generative diffusion process on general manifold. Instead of following the denoising approach of previous diffusion models, we construct a diffusion process using a mixture of bridge processes. We develop a geometric understanding of the mixture process, deriving the drift as a weighted mean of tangent directions to the data points.
  arXiv  Detail & Related papers  (2023-10-11T06:04:40Z)
• A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction [66.21060114843202]
  We propose a more general heat kernel based manifold embedding method that we call heat geodesic embeddings. Results show that our method outperforms existing state of the art in preserving ground truth manifold distances. We also showcase our method on single cell RNA-sequencing datasets with both continuum and cluster structure.
  arXiv  Detail & Related papers  (2023-05-30T13:58:50Z)
• Convolutional Filtering on Sampled Manifolds [122.06927400759021]
  We show that convolutional filtering on a sampled manifold converges to continuous manifold filtering. Our findings are further demonstrated empirically on a problem of navigation control.
  arXiv  Detail & Related papers  (2022-11-20T19:09:50Z)
• Riemannian Score-Based Generative Modeling [56.20669989459281]
  We introduce score-based generative models (SGMs) demonstrating remarkable empirical performance. Current SGMs make the underlying assumption that the data is supported on a Euclidean manifold with flat geometry. This prevents the use of these models for applications in robotics, geoscience or protein modeling.
  arXiv  Detail & Related papers  (2022-02-06T11:57:39Z)

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.