Deep Video Harmonization by Improving Spatial-temporal Consistency

doi:10.1007/s11633-023-1447-3

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Deep Video Harmonization by Improving Spatial-temporal Consistency
	Xiuwen Chen; Li Fang; Long Ye; Qin Zhang
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:1 页码:46-54
摘要	Video harmonization is an important step in video editing to achieve visual consistency by adjusting foreground appearances in both spatial and temporal dimensions. Previous methods always only harmonize on a single scale or ignore the inaccuracy of flow estimation, which leads to limited harmonization performance. In this work, we propose a novel architecture for video harmonization by making full use of spatiotemporal features and yield temporally consistent harmonized results. We introduce multiscale harmonization by using nonlocal similarity on each scale to make the foreground more consistent with the background. We also propose a foreground temporal aggregator to dynamically aggregate neighboring frames at the feature level to alleviate the effect of inaccurate estimated flow and ensure temporal consistency. The experimental results demonstrate the superiority of our method over other state-of-the-art methods in both quantitative and visual comparisons.
关键词	Harmonization, temporal consistency, video editing, video composition, nonlocal similarity
DOI	10.1007/s11633-023-1447-3
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56024
专题	学术期刊_Machine Intelligence Research
作者单位	Key Laboratory of Media Audio and Video Ministry of Education, Communication University of China, Beijing 100024, China
推荐引用方式 GB/T 7714	Xiuwen Chen,Li Fang,Long Ye,et al. Deep Video Harmonization by Improving Spatial-temporal Consistency[J]. Machine Intelligence Research,2024,21(1):46-54.
APA	Xiuwen Chen,Li Fang,Long Ye,&Qin Zhang.(2024).Deep Video Harmonization by Improving Spatial-temporal Consistency.Machine Intelligence Research,21(1),46-54.
MLA	Xiuwen Chen,et al."Deep Video Harmonization by Improving Spatial-temporal Consistency".Machine Intelligence Research 21.1(2024):46-54.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-11-366.R1.p（3779KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载