paper-with-me

Papers

Beyond Blur: A Fluid Perspective on Generative Diffusion Models

2025-06-20 · Grzegorz Gruszczynski, Michal Jan Wlodarczyk, Jakub J Meixner, Przemyslaw Musialski

We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward pass formulates image corruption via a physically motivated PDE that couples directional advection with isotropic diffusion and Gaussian noise, controlled by dimensionless numbers (Peclet, Fourier). We implement this PDE numerically through a GPU-accelerated custom Lattice Boltzmann solver for fast evaluation. To induce realistic turbulence, we generate stochastic velocity fields that introduce coherent motion and capture multi-scale mixing. In the generative process, a neural network learns to reverse the advection-diffusion operator thus constituting a novel generative model. We discuss how previous methods emerge as specific cases of our operator, demonstrating that our framework generalizes prior PDE-based corruption techniques. We illustrate how advection improves the diversity and quality of the generated images while keeping the overall color palette unaffected. This work bridges fluid dynamics, dimensionless PDE theory, and deep generative modeling, offering a fresh perspective on physically informed image corruption processes for diffusion-based synthesis.

📄 PDF Abstract BibTeX arXiv:2506.16827

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityGPUImage Generation

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

Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models

2025-11-21 · Hao-Chien Hsueh, Chi-En Yen, Wen-Hsiao Peng, Ching-Chun Huang arxiv

Diffusion probabilistic models have achieved remarkable success in generative tasks across diverse data types. While recent studies have explored alternative degradation processes beyond Gaussian noise, this paper bridge…

Image Generation

Improving Sample Quality of Diffusion Models Using Self-Attention Guidance

2022-10-03 · ICCV 2023 1 · Susung Hong, Gyuseong Lee, Wooseok Jang, Seungryong Kim

Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, s…

DenoisingDiversityImage Generation

A Denoising Diffusion Model for Fluid Field Prediction

2023-01-27 · Gefan Yang, Stefan Sommer

We propose a novel denoising diffusion generative model for predicting nonlinear fluid fields named FluidDiff. By performing a diffusion process, the model is able to learn a complex representation of the high-dimensiona…

DenoisingmodelPrediction

Blurring Diffusion Models

2022-09-12 · Emiel Hoogeboom, Tim Salimans

Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion. Here, we show that blurr…

DenoisingInductive Bias

Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis

2022-07-16 · Sangyun Lee, Hyungjin Chung, Jaehyeon Kim, Jong Chul Ye

Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly works well, is this the best way to gene…

DeblurringImage GenerationInductive Bias