PartDiff: Image Super-resolution with Partial Diffusion Models

by   Kai Zhao, et al.

Denoising diffusion probabilistic models (DDPMs) have achieved impressive performance on various image generation tasks, including image super-resolution. By learning to reverse the process of gradually diffusing the data distribution into Gaussian noise, DDPMs generate new data by iteratively denoising from random noise. Despite their impressive performance, diffusion-based generative models suffer from high computational costs due to the large number of denoising steps.In this paper, we first observed that the intermediate latent states gradually converge and become indistinguishable when diffusing a pair of low- and high-resolution images. This observation inspired us to propose the Partial Diffusion Model (PartDiff), which diffuses the image to an intermediate latent state instead of pure random noise, where the intermediate latent state is approximated by the latent of diffusing the low-resolution image. During generation, Partial Diffusion Models start denoising from the intermediate distribution and perform only a part of the denoising steps. Additionally, to mitigate the error caused by the approximation, we introduce "latent alignment", which aligns the latent between low- and high-resolution images during training. Experiments on both magnetic resonance imaging (MRI) and natural images show that, compared to plain diffusion-based super-resolution methods, Partial Diffusion Models significantly reduce the number of denoising steps without sacrificing the quality of generation.


page 1

page 2

page 7

page 8

page 9

page 10

page 11

page 12


Image Super-Resolution via Iterative Refinement

We present SR3, an approach to image Super-Resolution via Repeated Refin...

Pyramidal Denoising Diffusion Probabilistic Models

Diffusion models have demonstrated impressive image generation performan...

Accelerating Diffusion Models via Early Stop of the Diffusion Process

Denoising Diffusion Probabilistic Models (DDPMs) have achieved impressiv...

Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models

This work aims to improve the applicability of diffusion models in reali...

MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion

Patient scans from MRI often suffer from noise, which hampers the diagno...

Boomerang: Local sampling on image manifolds using diffusion models

Diffusion models can be viewed as mapping points in a high-dimensional l...

HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Models

Despite the proven significance of hyperspectral images (HSIs) in perfor...

Please sign up or login with your details

Forgot password? Click here to reset