Recent StyleGAN-based face swapping methods have been able to generate very realistic high-resolution face swapping results,but they are often plagued by the challenge of maintaining various attributes(such as express...Recent StyleGAN-based face swapping methods have been able to generate very realistic high-resolution face swapping results,but they are often plagued by the challenge of maintaining various attributes(such as expression,pose,and illumination).One reason is that these methods usually focus on the latent codes of facial semantic features corresponding to the W/W+space,and latent codes in these spaces are often highly entangled.To address this issue,we propose a new method,LDSwap.for disentangling and re-fusing latent codes in the StyleSpace.The semanticrelated latent code disentangling module(SLDM)we propose can successfully achieve facial semantic feature exchange and reorganization by disentangling latent codes.In addition,we propose a channel-split adaptive feature fusion module(CAFF)that adaptively learns and refuses spatial information in the target image.This module can learn spatial features from the target image without interference from the features of the target face region.Through qualitative and quantitative evaluation,we demonstrate that LDSwap shows significant improvements over three state-of-theart methods in maintaining the appearance of semantic features.展开更多
脑机接口(brain-computer interface,BCI)的分类性能一定程度上取决于对脑电信号的预处理方法,这项研究提出了一种空域时域滤波的预处理方法,以解决人类视觉系统中的潜伏延迟对编码调制视觉诱发电位(c-VEP) BCI的目标识别性能的影响。...脑机接口(brain-computer interface,BCI)的分类性能一定程度上取决于对脑电信号的预处理方法,这项研究提出了一种空域时域滤波的预处理方法,以解决人类视觉系统中的潜伏延迟对编码调制视觉诱发电位(c-VEP) BCI的目标识别性能的影响。基于一个平均信号和单次试验信号之间的最小均方误差(the least mean square error,LMSE)创建时域空域滤波器,并且通过最小绝对收缩和选择算子(the least absolute shrinkage and selection operator,LASSO)将稀疏约束应用于滤波器的权重系数,并用模板匹配法来对目标进行识别。将算法应用于由63比特的M序列及其循环移位序列调制的16个目标的c-VEP BCI,并与通用的空域滤波算法典型相关分析(CCA)及空域时域逆滤波算法进行比较。结果表明本研究所提出的算法在分类准确率方面优于其他两种算法。展开更多
基金support of the National Natural Science Foundation of China(Nos.62002070 and 82001331).
文摘Recent StyleGAN-based face swapping methods have been able to generate very realistic high-resolution face swapping results,but they are often plagued by the challenge of maintaining various attributes(such as expression,pose,and illumination).One reason is that these methods usually focus on the latent codes of facial semantic features corresponding to the W/W+space,and latent codes in these spaces are often highly entangled.To address this issue,we propose a new method,LDSwap.for disentangling and re-fusing latent codes in the StyleSpace.The semanticrelated latent code disentangling module(SLDM)we propose can successfully achieve facial semantic feature exchange and reorganization by disentangling latent codes.In addition,we propose a channel-split adaptive feature fusion module(CAFF)that adaptively learns and refuses spatial information in the target image.This module can learn spatial features from the target image without interference from the features of the target face region.Through qualitative and quantitative evaluation,we demonstrate that LDSwap shows significant improvements over three state-of-theart methods in maintaining the appearance of semantic features.
文摘脑机接口(brain-computer interface,BCI)的分类性能一定程度上取决于对脑电信号的预处理方法,这项研究提出了一种空域时域滤波的预处理方法,以解决人类视觉系统中的潜伏延迟对编码调制视觉诱发电位(c-VEP) BCI的目标识别性能的影响。基于一个平均信号和单次试验信号之间的最小均方误差(the least mean square error,LMSE)创建时域空域滤波器,并且通过最小绝对收缩和选择算子(the least absolute shrinkage and selection operator,LASSO)将稀疏约束应用于滤波器的权重系数,并用模板匹配法来对目标进行识别。将算法应用于由63比特的M序列及其循环移位序列调制的16个目标的c-VEP BCI,并与通用的空域滤波算法典型相关分析(CCA)及空域时域逆滤波算法进行比较。结果表明本研究所提出的算法在分类准确率方面优于其他两种算法。
