论文标题
区域意识的面部交换
Region-Aware Face Swapping
论文作者
论文摘要
本文提出了一个新颖的区域意识交换（RAFSWAP）网络，以局部全球范围的方式实现与身份吻合的和谐的高分辨率高分辨率发电：\ textbf {1）}本地面部面部区域敏感（FRA）分支通过引入有效模型的跨界互动式互动互动的跨度互动互动的互动互动的互动式互动互动的互联网。 \ textbf {2）}全局源特征 - 自动（SFA）分支进一步补充了与全局身份相关的线索，以生成身份符合的交换面。此外，我们提出了一个与stylegan2合并的模块\ textit {face toduredor}（fmp）模块，以一种无监督的方式预测与身份相关的柔软面膜，这对于产生和谐的高分辨率面孔更为实用。大量实验在定性和定量上证明了我们方法的优越性，该方法比SOTA方法生成更符合身份的高分辨率交换面，\ eg获得了96.70 ID检索，以优于SOTA MEGAFS以5.87 $ \ uparrow $。
This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction. \textbf{2)} Global Source Feature-Adaptive (SFA) branch further complements global identity-relevant cues for generating identity-consistent swapped faces. Besides, we propose a \textit{Face Mask Predictor} (FMP) module incorporated with StyleGAN2 to predict identity-relevant soft facial masks in an unsupervised manner that is more practical for generating harmonious high-resolution faces. Abundant experiments qualitatively and quantitatively demonstrate the superiority of our method for generating more identity-consistent high-resolution swapped faces over SOTA methods, \eg, obtaining 96.70 ID retrieval that outperforms SOTA MegaFS by 5.87$\uparrow$.
