Multi-scale Attention GAN with Adaptive Feature Fusion for Unsupervised Animation Face Generation

In this paper, we propose a novel generator architecture to translate a selfie photo into an animation face image in an unsupervised way. Recent face translation works often fail to preserve the characteristics of facial parts of selfie photos while transferring to animation images. To cope with this, the proposed method develops new Generative Adversarial Network (GAN) architecture composed of (1) simple cycle contents loss, (2) multi-scale assisted self-attention, and (3) adaptive feature fusion. The goal of using cycle contents loss is to make the GAN preserve a wide range of selfie image contents, which includes hair shape, facial expression and shape of face. In addition, multi-scale assisted self-attention complements the existing attention by using its various scales of self-attentions. Adaptive feature fusion helps model to understand the importance of each self-attention map among the multiple self-attention maps generated by the multi-scale self-attention module. Our extensive and comparative experiments on Selfie2Anime and Photo2Anime datasets have been performed to demonstrate the effectiveness of our method over other state-of-the-art methods.