DICE: 通过对比子空间分解在扩散模型中解构艺术家风格与内容
From Concept Erasure to Style Purification: Contrastive Eigenbases for Artist Style Protection
AI总结：
DICE通过对比子空间分解在扩散模型中解构艺术家风格与内容，实现无需训练的实时风格消除，提升部署端安全性。
摘要：
最近扩散模型的普及使风格模仿变得容易，使用户能够无需授权就模仿独特的艺术风格。在部署平台上，这引发了版权和知识产权风险，并要求有可靠的保护措施。然而，现有的应对措施要么需要随着新风格的出现而进行昂贵的权重编辑，要么依赖于显式指定的编辑风格，限制了它们在部署端的安全性。为了解决这一挑战，我们提出了DICE（通过对比子空间分解在扩散模型中解构艺术家风格与内容），这是一个无需训练的实时艺术家风格消除框架。与需要显式指定替代风格的风格编辑不同，DICE执行风格净化，去除艺术家的特征，同时保留用户意图的内容。我们的核心见解是，模型无法仅凭单个文本或图像真正理解艺术家的风格。因此，我们放弃传统上从孤立样本中识别风格的范式。相反，我们构建对比三元组，迫使模型在潜在空间中区分风格和非风格特征。通过将这种解构过程正式化为一个可解的广义特征值问题，我们实现了对风格子空间的精确识别。此外，我们引入了一种自适应注意力解耦编辑策略，动态评估每个标记的风格浓度，并对QKV向量进行差异抑制和内容增强。广泛的实验表明，DICE在彻底清除风格和保持内容完整性之间实现了优越的平衡。DICE仅增加了3秒的额外开销来解构风格，提供了一种实用且高效的遏制风格模仿的技术。
英文摘要：
Text-to-image diffusion models can reproduce specific artists visual styles at extremely low cost, raising copyright and deployment safety concerns about unauthorized style mimicry. Existing model-side protection methods generally follow ordinary concept erasure, emphasizing aggressive deletion or redirection of target styles. However, our causal intervention analysis shows that the central issue is not insufficient erasure strength, but a mismatch between artist styles and this paradigm: unlike ordinary object concepts, artist styles do not form compact, localized editable semantic units. Consequently, sparse editing and fixed retain lists struggle to suppress target styles while preserving generation utility. We therefore reformulate artist style protection as style purification, suppressing target style expression during inference while preserving the requested content and visual structure. We propose CAPE (Contrastive Artist Style Purification with Eigenbases), a training-free framework against artist style mimicry. CAPE constructs contrastive triplets around the target request and formulates style direction estimation as a generalized eigenvalue problem, capturing style-related directions that remain stable across content variations and are less affected by shared content. During inference, CAPE employs the Adaptive Suppression Controller to assign suppression strengths to different tokens based on Q, K, and V responses, and performs target style suppression on the K and V paths of self-attention. Experimental results show that CAPE effectively weakens target artist characteristics, including brushstrokes, textures, and local color processing, while better preserving major semantic entities, scene composition, and visual structures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
