FSA-Net:A Cost-efficient Face Swapping Attention Network with Occlusion-Aware Normalization  

作　　者：Zhipeng Bin Huihuang Zhao Xiaoman Liang Wenli Chen 

机构地区：[1]College of Computer Science and Technology,Hengyang Normal University,Hengyang,421002,China [2]Hunan Provincial Key Laboratory of Intelligent Information Processing and Application,Hengyang,421002,China

出　　处：《Intelligent Automation & Soft Computing》2023年第7期971-983,共13页智能自动化与软计算（英文）

基　　金：supported by the National Natural Science Foundation of China(No.61772179);the Hunan Provincial Natural Science Foundation of China(No.2020JJ4152,No.2022JJ50016);the science and technology innovation Program of Hunan Province(No.2016TP1020);the Scientific Research Fund of Hunan Provincial Education Department(No.21B0649);the Double First-Class University Project of Hunan Province(Xiangjiaotong[2018]469).

摘　　要：The main challenges in face swapping are the preservation and adaptive superimposition of attributes of two images.In this study,the Face Swapping Attention Network(FSA-Net)is proposed to generate photoreal-istic face swapping.The existing face-swapping methods ignore the blending attributes or mismatch the facial keypoint(cheek,mouth,eye,nose,etc.),which causes artifacts and makes the generated face silhouette non-realistic.To address this problem,a novel reinforced multi-aware attention module,referred to as RMAA,is proposed for handling facial fusion and expression occlusion flaws.The framework includes two stages.In the first stage,a novel attribute encoder is proposed to extract multiple levels of target face attributes and integrate identities and attributes when synthesizing swapped faces.In the second stage,a novel Stochastic Error Refinement(SRE)module is designed to solve the problem of facial occlusion,which is used to repair occlusion regions in a semi-supervised way without any post-processing.The proposed method is then compared with the current state-of-the-art methods.The obtained results demonstrate the qualitative and quantitative outperformance of the proposed method.More details are provided at the footnote link and at https://sites.google.com/view/fsa-net-official.

关 键 词：Attention face-swapping neural network face manipulation identity swap image translation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]