Residual Denoising Diffusion Models

by   Jiawei Liu, et al.

Current diffusion-based image restoration methods feed degraded input images as conditions into the noise estimation network. However, interpreting this diffusion process is challenging since it essentially generates the target image from the noise. To establish a unified and more interpretable model for image generation and restoration, we propose residual denoising diffusion models (RDDM). In contrast to existing diffusion models (e.g., DDPM or DDIM) that focus solely on noise estimation, our RDDM predicts residuals to represent directional diffusion from the target domain to the input domain, while concurrently estimating noise to account for random perturbations in the diffusion process. The introduction of residuals allows us to redefine the forward diffusion process, wherein the target image progressively diffuses into a purely noisy image or a noise-carrying input image, thus unifying image generation and restoration. We demonstrate that our sampling process is consistent with that of DDPM and DDIM through coefficient transformation, and propose a partially path-independent generation process to better understand the reverse process. Notably, with native support for conditional inputs, our RDDM enables a generic UNet, trained with only an ℓ _1 loss and a batch size of 1, to compete with state-of-the-art image restoration methods. We provide code and pre-trained models to encourage further exploration, application, and development of our innovative framework (


page 7

page 8

page 18

page 20

page 21

page 22

page 23

page 24


Gradpaint: Gradient-Guided Inpainting with Diffusion Models

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

ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories

Diffusion models have recently exhibited remarkable abilities to synthes...

A Unified Conditional Framework for Diffusion-based Image Restoration

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

Unlimited-Size Diffusion Restoration

Recently, using diffusion models for zero-shot image restoration (IR) ha...

Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models

Image restoration under adverse weather conditions has been of significa...

Artifact Restoration in Histology Images with Diffusion Probabilistic Models

Histological whole slide images (WSIs) can be usually compromised by art...

DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration

Diffusion models have recently received a surge of interest due to their...

Please sign up or login with your details

Forgot password? Click here to reset