通过优化语义锚点，精准擦除图像中的版权动画角色。
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
- 用结构与细节约束优化角色锚点嵌入，实现可控擦除。
- 在不损失图像质量前提下，达到顶尖擦除效果，支持多角色删除。
- 可直接接入现有方法提升性能，适合版权保护场景使用。
文本到图像扩散模型的强大生成能力引发了版权问题，尤其是未经授权复制动画角色。现有概念擦除方法在处理动画角色时存在不足：模型修改类方法难以为多样且高度独特的角色找到合适锚点；基于提示词的调控方法缺乏细粒度控制，难以精准干预。这些方法常导致擦除不完全或图像保真度下降，限制了实际应用。本文提出一种在模型连续文本表示上操作的可控擦除方法，在生成阶段擦除目标角色。我们通过结构和细节约束优化一个锚点嵌入作为角色替代，再采用结构感知自适应策略替换相关嵌入。实验表明，该方法在擦除效果和图像保真度方面均达到当前最优水平，支持可控擦除程度、多目标移除及模型迁移能力。此外，优化后的锚点可即插即用，提升现有模型修改基线的擦除性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。