A coupled RGB diffusion model conditioned on MLLM hidden-state embeddings performs reference-free single-image facial demorphing and outperforms latent-space and ViT baselines in ablations.
MorphGANformer: Transformer-based face morphing and de-morphing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhancing Single-Image Facial Demorphing using Multimodal Large Language Models
A coupled RGB diffusion model conditioned on MLLM hidden-state embeddings performs reference-free single-image facial demorphing and outperforms latent-space and ViT baselines in ablations.