2CET-GAN: Pixel-Level GAN Model for Human Facial Expression Transfer
This addresses limitations in existing GAN models for facial expression transfer, offering an unsupervised approach for applications in animation or human-computer interaction, though it is incremental as it builds on CycleGAN and InfoGAN.
The paper tackles the problem of transferring facial expressions between human faces without relying on emotion labels, proposing 2CET-GAN to learn continuous expression transfer and generate diverse, high-quality expressions that generalize to unknown identities.
Recent studies have used GAN to transfer expressions between human faces. However, existing models have many flaws: relying on emotion labels, lacking continuous expressions, and failing to capture the expression details. To address these limitations, we propose a novel CycleGAN- and InfoGAN-based network called 2 Cycles Expression Transfer GAN (2CET-GAN), which can learn continuous expression transfer without using emotion labels. The experiment shows our network can generate diverse and high-quality expressions and can generalize to unknown identities. To the best of our knowledge, we are among the first to successfully use an unsupervised approach to disentangle expression representation from identities at the pixel level.