Open access
2026
SSGLD: Spatial-Semantic Guided Latent Diffusion for Person Image Synthesis
Results show that SSGLD effectively resolves the trade-off between texture fidelity and pose-variation robustness in high-resolution paired PGPIS under sparse 2D skeleton conditioning.
Yi-Heng Xu, Zhen-Yin Zhang, Geng-Shen Chen
· IEEE Access · 0 citations