SHMT is a self-supervised latent-diffusion makeup transfer method that decouples face content and makeup and reconstructs the input, avoiding pseudo-paired training data.
Joint 3d face reconstruction and dense alignment with position map regression network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
SHMT is a self-supervised latent-diffusion makeup transfer method that decouples face content and makeup and reconstructs the input, avoiding pseudo-paired training data.