Facial aging and facial rejuvenation analyze a given face photograph to predict a future look or estimate a past look of the person. To achieve this, it is critical to preserve human identity and the corresponding aging progression and regression with high accuracy. However, existing methods cannot simultaneously handle these two objectives well. We propose a novel generative adversarial network based approach, named the Conditional Multi-Adversarial AutoEncoder with Ordinal Regression (CMAAE-OR). It utilizes an age estimation technique to control the aging accuracy and takes a high-level feature representation to preserve personalized identity. Specifically, the face is first mapped to a latent vector through a convolutional encoder. The latent vector is then projected onto the face manifold conditional on the age through a deconvolutional generator. The latent vector preserves personalized face features and the age controls facial aging and rejuvenation. A discriminator and an ordinal regression are imposed on the encoder and the generator in tandem, making the generated face images to be more photorealistic while simultaneously exhibiting desirable aging effects. Besides, a high-level feature representation is utilized to preserve personalized identity of the generated face. Experiments on two benchmark datasets demonstrate appealing performance of the proposed method over the state-of-the-art.
翻译:面部变化和面部再生分析一个给定的面部照片,以预测未来外观或估计一个人的过去外观。要做到这一点,关键是要保持人的身份以及相应的老化步进和回归,但现有方法不能同时很好地处理这两个目标。我们提出一种新的基因化对抗网络法,名为“多反向多反向自动编码器”和“圆形后退”(CMAAE-OR)。它使用年龄估计技术来控制老化的准确性,并采用高层次特征显示来保存个性化特征。具体地说,脸部首先通过一个相动编码器被映射到潜藏矢量上。然后通过一个变形生成器将潜在矢量投到一个年龄的多重条件上。潜向矢量保留个性化的面貌特征和年龄控制面部老化和再生化。对编码器和发电机同步实施歧视性和反向回归,使生成的面部位图像在同时呈现理想的个性化效果。此外,还将通过一个高层次的实验性特征显示工具,用以维护个人生成的状态。