Kuramoto Orientation Diffusion Models

• URL: http://arxiv.org/abs/2509.15328v2
• Date: Mon, 27 Oct 2025 02:01:46 GMT
• Title: Kuramoto Orientation Diffusion Models
• Authors: Yue Song, T. Anderson Keller, Sevan Brodjian, Takeru Miyato, Yisong Yue, Pietro Perona, Max Welling,
• Abstract summary: Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular patterns.<n>Motivated by the role of phase synchronization in biological systems, we propose a score-based generative model.<n>We implement competitive results on general image benchmarks and significantly improves generation quality on orientation-dense datasets like fingerprints and textures.
• Score: 67.0711709825854
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular directional patterns that are challenging to model using standard generative approaches based on isotropic Euclidean diffusion. Motivated by the role of phase synchronization in biological systems, we propose a score-based generative model built on periodic domains by leveraging stochastic Kuramoto dynamics in the diffusion process. In neural and physical systems, Kuramoto models capture synchronization phenomena across coupled oscillators -- a behavior that we re-purpose here as an inductive bias for structured image generation. In our framework, the forward process performs \textit{synchronization} among phase variables through globally or locally coupled oscillator interactions and attraction to a global reference phase, gradually collapsing the data into a low-entropy von Mises distribution. The reverse process then performs \textit{desynchronization}, generating diverse patterns by reversing the dynamics with a learned score function. This approach enables structured destruction during forward diffusion and a hierarchical generation process that progressively refines global coherence into fine-scale details. We implement wrapped Gaussian transition kernels and periodicity-aware networks to account for the circular geometry. Our method achieves competitive results on general image benchmarks and significantly improves generation quality on orientation-dense datasets like fingerprints and textures. Ultimately, this work demonstrates the promise of biologically inspired synchronization dynamics as structured priors in generative modeling.

Related papers

• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models [0.0]
  We introduce Spectral Generative Flow Models (SGFMs), a physics-inspired alternative to transformer-based large language models.<n>Instead of representing text or video as sequences of discrete tokens processed by attention, SGFMs treat generation as the evolution of a continuous field governed by constrained dynamics.
  arXiv  Detail & Related papers  (2026-01-13T12:50:24Z)
• The Mean-Field Dynamics of Transformers [6.008788032203683]
  By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein gradient flows (Kuramoto), and mean-shift clustering.<n>Results highlight both the mechanisms that drive representation collapse and the regimes that preserve expressive, multi-cluster structure in deep attention architectures.
  arXiv  Detail & Related papers  (2025-12-01T16:51:00Z)
• Consistent World Models via Foresight Diffusion [56.45012929930605]
  We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
  arXiv  Detail & Related papers  (2025-05-22T10:01:59Z)
• Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignment [0.0]
  We present a mutually aligned diffusion framework for cross-modal biomechanical motion generation.<n>By treating each modality as complementary observations of a shared underlying locomotor dynamical system, our method aligns latent representations at each diffusion step.<n>Our approach is motivated by the fact that local time windows of $X$ and $Y$ represent the same phase of an underlying dynamical system.
  arXiv  Detail & Related papers  (2025-03-15T17:44:03Z)
• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [71.63194926457119]
  We introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes.<n>Experiments across scientifictemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks.
  arXiv  Detail & Related papers  (2025-03-02T16:10:32Z)
• Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method [60.88467353578118]
  We show that a fixed-point-inspired iterative approach to invert real-world images does not achieve convergence, instead oscillating between distinct clusters. We introduce a simple and fast distribution transfer technique that facilitates image enhancement, stroke-based recoloring, as well as visual prompt-guided image editing.
  arXiv  Detail & Related papers  (2024-11-17T17:45:37Z)
• How to Bridge Spatial and Temporal Heterogeneity in Link Prediction? A Contrastive Method [11.719027225797037]
  We propose a novel textbfContrastive Learning-based textbfLink textbfPrediction model, textbfCLP.<n>Our mymodel consistently outperforms the state-of-the-art models, demonstrating an average improvement of 10.10%, 13.44% in terms of AUC and AP.
  arXiv  Detail & Related papers  (2024-11-01T14:20:53Z)
• Edge-preserving noise for diffusion models [4.435514696080208]
  We present a novel edge-preserving diffusion model that generalizes over existing isotropic models.<n>We show that our model's generative process converges faster to results that more closely match the target distribution.<n>Our edge-preserving diffusion process consistently outperforms state-of-the-art baselines in unconditional image generation.
  arXiv  Detail & Related papers  (2024-10-02T13:29:52Z)
• Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression [63.56922682378755]
  We focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding. The proposed adaptive aggregation generates kernel offsets to capture valid information in the content-conditioned range to help transform. Experimental results demonstrate that our method achieves superior rate-distortion performance on three benchmarks compared to the state-of-the-art learning-based methods.
  arXiv  Detail & Related papers  (2023-08-17T01:34:51Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows [0.0]
  We develop continuous spin-glass distributions with normalizing flows to model correlations in generic discrete problems. We demonstrate that key physical and computational properties of the spin-glass phase can be successfully learned. Remarkably, we observe that the learning itself corresponds to a spin-glass phase transition within the layers of the trained normalizing flows.
  arXiv  Detail & Related papers  (2020-01-02T19:00:01Z)

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.