A self-supervised 6D latent space of material appearance, learned without human labels, enables controllable appearance transfer and editing in a diffusion pipeline.
Isolating sources of disentanglement in varia- tional autoencoders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Controllable Appearance Representation for Flexible Transfer and Editing
A self-supervised 6D latent space of material appearance, learned without human labels, enables controllable appearance transfer and editing in a diffusion pipeline.