Open access
2026
High-Fidelity Human Pose Transfer: A Unified Framework With Hierarchical Semantic Alignment and Gated Residual Fusion
A unified generative adversarial network (GAN) framework that integrates three novel, complementary mechanisms that generates high-fidelity, structurally faithful results from a single reference image, offering a robust solution for applications in virtual try-on, animation, and human image synthesis under challenging pose transformations.
Tao Jiang, Guangyong Zheng, Songshui Wu et al.
· IEEE Access · 0 citations