增强型运动转移StyleGAN用于生成多样化猕猴面部表情
Motion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions
AI总结：
本文提出利用StyleGAN2生成猕猴面部表情，通过运动转移增强数据，改进训练集多样性与精度，实现更丰富的表情生成。
摘要：
生成动物面部使用生成AI技术具有挑战性，因为可用训练图像在数量和变化上都有限，特别是跨个体的面部表情。本研究聚焦于广泛研究的猕猴，提出使用基于风格的生成图像模型（即StyleGAN2）生成其面部表情。为解决数据限制，我们实现了：1）通过运动转移合成新的面部表情图像以动画静态图像；2）基于初始训练StyleGAN2模型的猕猴面部潜在表示进行样本选择，确保训练数据集的多样性和均匀采样；3）损失函数优化以确保准确再现细微运动，如眼运动。结果表明，所提方法能够生成多种猕猴个体的面部表情，优于仅训练于原始静态图像的模型。此外，我们展示模型在基于风格的图像编辑中有效，特定风格参数对应不同的面部运动。这些发现强调了模型解构运动组件作为风格参数的潜力，为猕猴面部表情研究提供了有价值的工具。
英文摘要：
Generating animal faces using generative AI techniques is challenging because the available training images are limited both in quantity and variation, particularly for facial expressions across individuals. In this study, we focus on macaque monkeys, widely studied in systems neuroscience and evolutionary research, and propose a method to generate their facial expressions using a style-based generative image model (i.e., StyleGAN2). To address data limitations, we implemented: 1) data augmentation by synthesizing new facial expression images using a motion transfer to animate still images with computer graphics, 2) sample selection based on the latent representation of macaque faces from an initially trained StyleGAN2 model to ensure the variation and uniform sampling in training dataset, and 3) loss function refinement to ensure the accurate reproduction of subtle movements, such as eye movements. Our results demonstrate that the proposed method enables the generation of diverse facial expressions for multiple macaque individuals, outperforming models trained solely on original still images. Additionally, we show that our model is effective for style-based image editing, where specific style parameters correspond to distinct facial movements. These findings underscore the model's potential for disentangling motion components as style parameters, providing a valuable tool for research on macaque facial expressions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
