Related papers: Blurring Diffusion Models

Blurring Diffusion Models

URL: http://arxiv.org/abs/2209.05557v3
Date: Wed, 1 May 2024 10:53:54 GMT
Title: Blurring Diffusion Models
Authors: Emiel Hoogeboom, Tim Salimans,
Abstract summary: We show that blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. We propose a class of diffusion models that offers the best of both standard Gaussian denoising diffusion and inverse heat dissipation.
Score: 27.339469450737525
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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 blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. In making this connection, we bridge the gap between inverse heat dissipation and denoising diffusion, and we shed light on the inductive bias that results from this modeling choice. Finally, we propose a generalized class of diffusion models that offers the best of both standard Gaussian denoising diffusion and inverse heat dissipation, which we call Blurring Diffusion Models.

Related papers

G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving [55.185588994883226]
This paper presents a novel method for addressing linear inverse problems by leveraging image-generation models based on discrete diffusion as priors. To the best of our knowledge, this is the first approach to use discrete diffusion model-based priors for solving image inverse problems.
arXiv Detail & Related papers (2024-10-09T06:18:25Z)
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models [76.46246743508651]
We show that current diffusion models actually have an expressive bottleneck in backward denoising. We introduce soft mixture denoising (SMD), an expressive and efficient model for backward denoising.
arXiv Detail & Related papers (2023-09-25T12:03:32Z)
Eliminating Lipschitz Singularities in Diffusion Models [51.806899946775076]
We show that diffusion models frequently exhibit the infinite Lipschitz near the zero point of timesteps. This poses a threat to the stability and accuracy of the diffusion process, which relies on integral operations. We propose a novel approach, dubbed E-TSDM, which eliminates the Lipschitz of the diffusion model near zero.
arXiv Detail & Related papers (2023-06-20T03:05:28Z)
Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance [95.12230117950232]
We show that a common latent space emerges from two diffusion models trained independently on related domains. Applying CycleDiffusion to text-to-image diffusion models, we show that large-scale text-to-image diffusion models can be used as zero-shot image-to-image editors.
arXiv Detail & Related papers (2022-10-11T15:53:52Z)
Diffusion Models in Vision: A Survey [80.82832715884597]
A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
arXiv Detail & Related papers (2022-09-10T22:00:30Z)
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise [52.59444045853966]
We show that an entire family of generative models can be constructed by varying the choice of image degradation. The success of fully deterministic models calls into question the community's understanding of diffusion models.
arXiv Detail & Related papers (2022-08-19T15:18:39Z)
Non-Uniform Diffusion Models [0.8602553195689513]
We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows. We experimentally find that in the same or less training time, the multi-scale diffusion model achieves better FID score than the standard uniform diffusion model. We also show that non-uniform diffusion leads to a novel estimator for the conditional score function which achieves on par performance with the state-of-the-art conditional denoising estimator.
arXiv Detail & Related papers (2022-07-20T09:59:28Z)
Generative Modelling With Inverse Heat Dissipation [21.738877553160304]
We propose a new diffusion-like model that generates images through reversing the heat equation, a PDE that erases fine-scale information when run over the 2D plane of the image. Our new model shows emergent properties not seen in standard diffusion models, such as disentanglement of overall colour and shape in images.
arXiv Detail & Related papers (2022-06-21T13:40:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.