擦除但保留：通过优化语义锚点实现版权动画角色的可控移除
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
浏览论文内容
中文总结 AI 辅助
针对文本到图像扩散模型的动画角色版权问题，本文提出基于优化语义锚点的可控擦除方法，实现了更优的擦除效果与图像保真度，支持多目标移除与模型迁移。
中文摘要 AI 辅助
文本到图像扩散模型的卓越生成能力引发了版权担忧，尤其是动画角色的未经授权复制。现有概念擦除方法在动画角色擦除方面存在不足：模型修改方法难以针对多样、高度独特的角色识别合适的锚点；基于提示的引导方法缺乏精确干预的细粒度控制，这些方法常导致擦除不完整且图像保真度下降，阻碍了实际部署。本文提出一种作用于模型连续文本表示的可控方法，用于在生成过程中擦除目标角色。该方法通过结构和细节约束优化锚点嵌入，使其作为角色替代物，随后通过结构感知自适应策略将与目标相关的嵌入替换为该锚点。实验表明，本文方法达到了最先进的擦除效果和图像保真度保留，同时支持可控擦除程度、多目标移除和模型可迁移性。此外，优化后的锚点可即插即用至现有模型修改基线，以提升其擦除性能。
英文摘要
The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation characters. Existing concept erasure methods fall short for animation character erasure: model modification methods struggle to identify suitable anchors for diverse, highly distinctive characters; prompt-based steering methods lack fine-grained control for precise intervention. These approaches often yield incomplete erasure and degraded image fidelity, hindering real-world deployment. In this paper, we propose a controllable method operating on the model's continuous textual representation to erase target characters during generation. We optimizes an anchor embedding via structural and detailed constraints to serve as a character surrogate, then replaces target-related embeddings with the anchor via a structure-aware adaptive strategy. Experiments show that our method achieves state-of-the-art erasure effectiveness and image fidelity preservation, while supporting controllable erasure degree, multi-target removal, and model transferability. Moreover, our optimized anchors are plug-and-play with current model modification baselines to improve their erasure performance.
发表机构
- Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
- School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
机构由 AI 辅助整理，请以论文原文为准。
