DiFaReli++ conditions a DDIM on shading references and inferred shadow maps to relight single-view faces with consistent shadows, trained only on 2D images and claiming SOTA on Multi-PIE.
Diffusion autoencoders: Toward a meaningful and decodable representation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows
DiFaReli++ conditions a DDIM on shading references and inferred shadow maps to relight single-view faces with consistent shadows, trained only on 2D images and claiming SOTA on Multi-PIE.