Generative Diffusion Prior for Unified Image Restoration and Enhancement

by   Ben Fei, et al.

Existing image restoration methods mostly leverage the posterior distribution of natural images. However, they often assume known degradation and also require supervised training, which restricts their adaptation to complex real applications. In this work, we propose the Generative Diffusion Prior (GDP) to effectively model the posterior distributions in an unsupervised sampling manner. GDP utilizes a pre-train denoising diffusion generative model (DDPM) for solving linear inverse, non-linear, or blind problems. Specifically, GDP systematically explores a protocol of conditional guidance, which is verified more practical than the commonly used guidance way. Furthermore, GDP is strength at optimizing the parameters of degradation model during the denoising process, achieving blind image restoration. Besides, we devise hierarchical guidance and patch-based methods, enabling the GDP to generate images of arbitrary resolutions. Experimentally, we demonstrate GDP's versatility on several image datasets for linear problems, such as super-resolution, deblurring, inpainting, and colorization, as well as non-linear and blind issues, such as low-light enhancement and HDR image recovery. GDP outperforms the current leading unsupervised methods on the diverse benchmarks in reconstruction quality and perceptual quality. Moreover, GDP also generalizes well for natural images or synthesized images with arbitrary sizes from various tasks out of the distribution of the ImageNet training set.


page 29

page 31

page 32

page 33

page 35

page 37

page 39

page 41


Denoising Diffusion Restoration Models

Many interesting tasks in image restoration can be cast as linear invers...

A Unified Conditional Framework for Diffusion-based Image Restoration

Diffusion Probabilistic Models (DPMs) have recently shown remarkable per...

Perceptual Image Restoration with High-Quality Priori and Degradation Learning

Perceptual image restoration seeks for high-fidelity images that most li...

Blind Motion Deblurring through SinGAN Architecture

Blind motion deblurring involves reconstructing a sharp image from an ob...

DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models

Recent generative models show impressive results in photo-realistic imag...

VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance

Restoring degraded music signals is essential to enhance audio quality f...

Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors

Conditional diffusion probabilistic models can model the distribution of...

Please sign up or login with your details

Forgot password? Click here to reset