计算机应用研究2024，Vol.41Issue(4)：1214-1220,7.DOI:10.19734/j.issn.1001-3695.2023.07.0351
结合注意力机制与多尺度特征融合的视频彩色化方法
Video colorization method combining attention mechanism and multi-scale feature fusion
摘要
Abstract
To address the issue that existing video colorization methods are complicated to guarantee both coloring quality and temporal consistency,this paper proposed a video colorization method AMVC-GAN combining attention mechanism and multi-scale feature fusion.Firstly,it proposed a GAN-based video colorization network model.It designed a multi-scale feature fu-sion module in the generator of GAN with a cyclic time network as the main body to obtain information of different time fre-quencies.Secondly,to effectively consider the relationship between adjacent frames,it used the features extracted from diffe-rent time frequencies to strengthen the connection between frames as a way to enhance the temporal consistency of colorization.Finally,to obtain more helpful information,it introduced an attention module in the upsampling part,and optimally trained the results by utilizing PatchGAN to enhance the final colorization effect.Comparing with the state-of-the-art automatic video colo-rization methods on DAVIS and VIDEVO datasets,the results show that AMVC-GAN ranks first in multiple indicators,with better time consistency and colorization effect.Compared with other methods,AMVC-GAN can effectively reduce time flicker,while ensuring more real and natural colorization effect.关键词
生成对抗网络/多尺度融合/注意力机制/彩色化Key words
generating adversarial networks/multiscale fusion/attention mechanisms/colorization分类
信息技术与安全科学引用本文复制引用
周柯明,孔广黔,邓周灰..结合注意力机制与多尺度特征融合的视频彩色化方法[J].计算机应用研究,2024,41(4):1214-1220,7.基金项目
国家自然科学基金资助项目(62266011) （62266011）
贵州省基础研究计划资助项目(黔科合基础-ZK[2022]一般119) （黔科合基础-ZK[2022]一般119）
