Style-CCL uses curriculum continual learning on a million-scale synthetic dataset with a dual-branch SC-DiT to achieve state-of-the-art content-preserving style transfer.
Fast Imagic: Solving Overfitting in Text- guided Image Editing via Disentangled UNet with For- getting Mechanism and Unified Vision-Language Opti- mization
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
-
Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning
Style-CCL uses curriculum continual learning on a million-scale synthetic dataset with a dual-branch SC-DiT to achieve state-of-the-art content-preserving style transfer.