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

by   Ziwei Luo, et al.

This work aims to improve the applicability of diffusion models in realistic image restoration. Specifically, we enhance the diffusion model in several aspects such as network architecture, noise level, denoising steps, training image size, and optimizer/scheduler. We show that tuning these hyperparameters allows us to achieve better performance on both distortion and perceptual scores. We also propose a U-Net based latent diffusion model which performs diffusion in a low-resolution latent space while preserving high-resolution information from the original input for the decoding process. Compared to the previous latent-diffusion model which trains a VAE-GAN to compress the image, our proposed U-Net compression strategy is significantly more stable and can recover highly accurate images without relying on adversarial optimization. Importantly, these modifications allow us to apply diffusion models to various image restoration tasks, including real-world shadow removal, HR non-homogeneous dehazing, stereo super-resolution, and bokeh effect transformation. By simply replacing the datasets and slightly changing the noise network, our model, named Refusion, is able to deal with large-size images (e.g., 6000 x 4000 x 3 in HR dehazing) and produces good results on all the above restoration problems. Our Refusion achieves the best perceptual performance in the NTIRE 2023 Image Shadow Removal Challenge and wins 2nd place overall.


page 1

page 3

page 4

page 7

page 8


Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration

Inversion by Direct Iteration (InDI) is a new formulation for supervised...

PartDiff: Image Super-resolution with Partial Diffusion Models

Denoising diffusion probabilistic models (DDPMs) have achieved impressiv...

A Unified Conditional Framework for Diffusion-based Image Restoration

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

Boomerang: Local sampling on image manifolds using diffusion models

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

On the Importance of Noise Scheduling for Diffusion Models

We empirically study the effect of noise scheduling strategies for denoi...

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

Diffusion models (DMs) have recently been introduced in image deblurring...

DriftRec: Adapting diffusion models to blind image restoration tasks

In this work, we utilize the high-fidelity generation abilities of diffu...

Please sign up or login with your details

Forgot password? Click here to reset