paper-with-me

홈 › Papers

Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models

2022-10-21 · Vikram Voleti, Christopher Pal, Adam Oberman

Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural generative models. However, most contemporary state-of-the-art methods are derived from a standard isotropic Gaussian formulation. In this work we examine the situation where non-isotropic Gaussian distributions are used. We present the key mathematical derivations for creating denoising diffusion models using an underlying non-isotropic Gaussian noise model. We also provide initial experiments with the CIFAR-10 dataset to help verify empirically that this more general modeling approach can also yield high-quality samples.

📄 PDF Abstract BibTeX arXiv:2210.12254

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingDiversity

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

Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems

2025-05-15 · Jeffrey Alido, Tongyu Li, Yu Sun, Lei Tian

Conventional score-based diffusion models (DMs) may struggle with anisotropic Gaussian diffusion processes due to the required inversion of covariance matrices in the denoising score matching training objective \cite{vin…

Denoising

Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing

2023-09-21 · NeurIPS 2023 11

Score-based diffusion models (SBDMs) have achieved state-of-the-art results in image generation. In this paper, we propose a Non-isotropic Gaussian Diffusion Model (NGDM) for image editing, which requires editing the sou…

Edge-preserving noise for diffusion models

2024-10-02 · Jente Vandersanden, Sascha Holl, Xingchang Huang, Gurprit Singh

Classical generative diffusion models learn an isotropic Gaussian denoising process, treating all spatial regions uniformly, thus neglecting potentially valuable structural information in the data. Inspired by the long-e…

DenoisingImage GenerationUnconditional Image Generation

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

Exact Posterior Score Estimation for Solving Linear Inverse Problems

2026-06-15 · Abbas Mammadov, Ozgur Kara, Kaan Oktay, Iskander Azangulov 외 arxiv

Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption. To use this prior to solve a linear inverse problem, one needs to sample from the posterior, but the score…