{"slug": "style-ccl-content-preserving-style-transfer-via-curriculum-continual-learning", "title": "Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning", "summary": "Researchers propose Style-CCL, a multi-stage curriculum continual learning framework for content-preserving style transfer using Diffusion Transformers. The method trains a dual-branch SC-DiT from semantic to texture styles and from clean to synthetic data, achieving state-of-the-art performance in style similarity, content consistency, and aesthetic quality.", "body_md": "arXiv:2606.14746v1 Announce Type: new\nAbstract: Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to entangled content and style features. With a reverse triplet synthesis pipeline to build a million-scale training set and a dual-branch Style-Content DiT (SC-DiT) that decouples style and content via separate ROPE embeddings and causal masking, we observe that such a one-stage training paradigm on mixed style categories causes semantic styles to dominate, hindering texture style learning, and harming content preservation. To address these issues, we propose Style-CCL, a Multi-Stage Curriculum Continual Learning framework that trains SC-DiT from semantic (easy) to texture (hard) styles, and from clean to synthetic data, with Random Memory Rehearsal across stages to avoid catastrophic forgetting. Extensive experiments demonstrate that our Style-CCL achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality.", "url": "https://wpnews.pro/news/style-ccl-content-preserving-style-transfer-via-curriculum-continual-learning", "canonical_source": "https://arxiv.org/abs/2606.14746", "published_at": "2026-06-16 04:00:00+00:00", "updated_at": "2026-06-16 04:19:20.881673+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "generative-ai", "large-language-models"], "entities": ["Style-CCL", "SC-DiT", "Diffusion Transformers", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/style-ccl-content-preserving-style-transfer-via-curriculum-continual-learning", "markdown": "https://wpnews.pro/news/style-ccl-content-preserving-style-transfer-via-curriculum-continual-learning.md", "text": "https://wpnews.pro/news/style-ccl-content-preserving-style-transfer-via-curriculum-continual-learning.txt", "jsonld": "https://wpnews.pro/news/style-ccl-content-preserving-style-transfer-via-curriculum-continual-learning.jsonld"}}