Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models

TL;DR

This paper introduces Noise Calibration, a plug-and-play method that enhances video quality using pre-trained diffusion models while preserving content consistency, reducing training costs and improving synthesis results.

Contribution

It proposes a novel noise calibration technique that maintains content structure and enhances visual quality without retraining diffusion models.

Findings

Significant improvement in video enhancement quality.

Effective preservation of original content structure.

Reduced training costs compared to existing methods.

Abstract

In order to improve the quality of synthesized videos, currently, one predominant method involves retraining an expert diffusion model and then implementing a noising-denoising process for refinement. Despite the significant training costs, maintaining consistency of content between the original and enhanced videos remains a major challenge. To tackle this challenge, we propose a novel formulation that considers both visual quality and consistency of content. Consistency of content is ensured by a proposed loss function that maintains the structure of the input, while visual quality is improved by utilizing the denoising process of pretrained diffusion models. To address the formulated optimization problem, we have developed a plug-and-play noise optimization strategy, referred to as Noise Calibration. By refining the initial random noise through a few iterations, the content of original video can be largely preserved, and the enhancement effect demonstrates a notable improvement. Extensive experiments have demonstrated the effectiveness of the proposed method.