English

Region-Aware Face Swapping

Computer Vision and Pattern Recognition 2022-03-21 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2203.04564,
  title  = {Region-Aware Face Swapping},
  author = {Chao Xu and Jiangning Zhang and Miao Hua and Qian He and Zili Yi and Yong Liu},
  journal= {arXiv preprint arXiv:2203.04564},
  year   = {2022}
}
R2 v1 2026-06-24T10:06:59.246Z