AttDiff-GAN decouples attribute manipulation via feature-level adversarial learning and guides diffusion generation with the edited features, plus PriorMapper and RefineExtractor modules, to achieve more accurate edits and better non-target preservation on CelebA-HQ.
Infostyler: Disentanglement information bottleneck for artistic style transfer,
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
-
AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing
AttDiff-GAN decouples attribute manipulation via feature-level adversarial learning and guides diffusion generation with the edited features, plus PriorMapper and RefineExtractor modules, to achieve more accurate edits and better non-target preservation on CelebA-HQ.