Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model
This work addresses video quality issues for applications like media production and streaming, representing an incremental advancement by adapting existing image methods to video.
The paper tackles the problem of temporal flickering artifacts when applying pre-trained image diffusion models to video restoration and enhancement, proposing a framework that achieves improved temporal consistency through novel attention and sampling strategies.
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.