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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Qinyu, Chen, Haoxin, Zhang, Yong, Xia, Menghan, Cun, Xiaodong, Su, Zhixun, Shan, Ying
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909254457229312
author Yang, Qinyu
Chen, Haoxin
Zhang, Yong
Xia, Menghan
Cun, Xiaodong
Su, Zhixun
Shan, Ying
author_facet Yang, Qinyu
Chen, Haoxin
Zhang, Yong
Xia, Menghan
Cun, Xiaodong
Su, Zhixun
Shan, Ying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10285
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models
Yang, Qinyu
Chen, Haoxin
Zhang, Yong
Xia, Menghan
Cun, Xiaodong
Su, Zhixun
Shan, Ying
Computer Vision and Pattern Recognition
I.2; I.4.3
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.
title Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models
topic Computer Vision and Pattern Recognition
I.2; I.4.3
url https://arxiv.org/abs/2407.10285