Facial expression manipulation has gained wide attention and has been applied in various fields, such as film production, electronic games, and short videos. However, existing facial expression manipulation methods often overlook the details of local regions in images, resulting in the failure to preserve local structures and textures of images. To solve this problem, this paper proposes a local semantic segmentation mask-based GAN (LSGAN) to generate fine-grained facial expression images. LSGAN is composed of a semantic mask generator, an adversarial autoencoder, a transformative generator, and an AU-intensity discriminator. Our semantic mask generator generates eye, mouth, and cheek masks of face images. Then, our transformative generator integrates target expression labels and corresponding facial region features to generate a vivid target facial expression image. In this fashion, we can capture expressions from target face images explicitly. Furthermore, an AU-intensity discriminator is designed to capture facial expression variations and evaluate quality of generated images. Extensive experiments demonstrate that our method achieves authentic face images with accurate facial expressions and outperforms state-of-the-art methods qualitatively and quantitatively.

面部表情操纵受到广泛关注，并已应用于电影制作、电子游戏、短视频等各个领域。然而，现有的面部表情处理方法往往忽略图像中局部区域的细节，导致无法保留图像的局部结构和纹理。为了解决这个问题，本文提出了一种基于局部语义分割掩模的GAN（LSGAN）来生成细粒度的面部表情图像。 LSGAN 由语义掩码生成器、对抗性自动编码器、变换生成器和 AU 强度鉴别器组成。我们的语义掩模生成器生成人脸图像的眼睛、嘴巴和脸颊掩模。然后，我们的变换生成器集成目标表情标签和相应的面部区域特征，以生成生动的目标面部表情图像。通过这种方式，我们可以明确地从目标人脸图像中捕获表情。此外，AU 强度鉴别器旨在捕获面部表情变化并评估生成图像的质量。大量的实验表明，我们的方法可以实现具有准确面部表情的真实人脸图像，并且在定性和定量上都优于最先进的方法。