Deep Video Harmonization by Improving Spatial-temporal Consistency
文献类型:期刊论文
作者 | Xiuwen Chen, Li Fang, Long Ye, Qin Zhang |
刊名 | Machine Intelligence Research |
出版日期 | 2024 |
卷号 | 21期号:1页码:46-54 |
ISSN号 | 2731-538X |
关键词 | Harmonization, temporal consistency, video editing, video composition, nonlocal similarity |
DOI | 10.1007/s11633-023-1447-3 |
英文摘要 | 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. |
源URL | [http://ir.ia.ac.cn/handle/173211/54574] |
专题 | 自动化研究所_学术期刊_International Journal of Automation and Computing |
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, Qin Zhang. 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, Li Fang, Long Ye, Qin Zhang."Deep Video Harmonization by Improving Spatial-temporal Consistency".Machine Intelligence Research 21.1(2024):46-54. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。