AI RESEARCH

Improving Generative Adversarial Network Generalization for Facial Expression Synthesis

arXiv CS.LG

ArXi:2603.15648v1 Announce Type: cross Facial expression synthesis aims to generate realistic facial expressions while preserving identity. Existing conditional generative adversarial networks (GANs) achieve excellent image-to-image translation results, but their performance often degrades when test images differ from the