Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model

TL;DR

This paper introduces a zero-shot video restoration and enhancement framework leveraging a pre-trained image diffusion model, incorporating novel temporal attention and consistency strategies to reduce flickering artifacts and improve temporal coherence.

Contribution

It presents the first zero-shot video restoration framework based on image diffusion models, with new temporal attention and consistency techniques for improved video quality.

Findings

Outperforms existing methods in video restoration quality

Reduces temporal flickering artifacts effectively

Compatible as a plug-and-play module for diffusion models

Abstract

Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement. However, directly applying them to video restoration and enhancement results in severe temporal flickering artifacts. In this paper, we propose the first framework for zero-shot video restoration and enhancement based on the pre-trained image diffusion model. By replacing the spatial self-attention layer with the proposed short-long-range (SLR) temporal attention layer, the pre-trained image diffusion model can take advantage of the temporal correlation between frames. We further propose temporal consistency guidance, spatial-temporal noise sharing, and an early stopping sampling strategy to improve temporally consistent sampling. Our method is a plug-and-play module that can be inserted into any diffusion-based image restoration or enhancement methods to further improve their performance. Experimental results demonstrate the superiority of our proposed method. Our code is available at https://github.com/cao-cong/ZVRD.