STAGE：面向文本到3D模型的子空间定向仿射生成擦除

中文摘要 AI 辅助

概念擦除在抑制目标概念的同时，保持对无关输入的行为。现有的闭式方法专为2D图像扩散设计，并假设单一生成路径，因此一次编辑必须同时覆盖几何和纹理。原生3D生成器直接合成结构化3D表示，而非通过提升2D样本，违反了这一假设。我们表明，形状和物体概念必须在流程的结构阶段擦除，而材质概念在外观阶段擦除。因此，我们将原生文本到3D中的擦除表述为阶段感知的编辑问题，并引入STAGE，一种无需训练、闭式的框架。STAGE将每次编辑限制在由擦除嵌入与锚定嵌入之间的差异所张成的低维子空间中，并将先前编辑器的范数保持（正交）约束放宽为最小二乘仿射校正，该校正将目标激活映射到安全锚点，并对保留提示的位移施加惩罚。该校正适用于结构阶段、外观阶段或两者。我们发现，编辑必须到达的阶段由概念类型决定。在TRELLIS（标准的开源原生3D生成器）上，跨越15个形状、材质和物体概念，STAGE在综合得分上达到66.7，该得分平衡了遗忘目标概念与保留其他一切，聚合了基于CLIP的语义和物理指标，而最强适应基线为53.2。代码：此https URL 项目页面：此https URL

英文摘要

Concept erasure suppresses a target concept while preserving behavior on unrelated inputs. Existing closed-form methods were designed for 2D image diffusion and assume a single generative pathway, so one edit must cover geometry and texture at once. Native 3D generators, which synthesize structured 3D representations directly rather than by lifting 2D samples, violate this assumption. We show that shape and object concepts must be erased in the structural stage of the pipeline and material concepts in the appearance stage. We therefore formulate erasure in native text-to-3D as a stage-aware editing problem and introduce STAGE, a training-free, closed-form framework. STAGE confines each edit to the low-dimensional subspace spanned by the differences between erase and anchor embeddings, and relaxes the norm-preserving (orthogonal) constraint of prior editors into a least-squares affine correction that maps target activations onto safe anchors subject to a penalty on the displacement of retained prompts. The correction applies to the structural stage, the appearance stage, or both. We find that the stage an edit must reach is determined by concept type. On TRELLIS, the standard open native 3D generator, across 15 shape, material, and object concepts, STAGE reaches 66.7 on a composite score that balances forgetting the target concept against preserving everything else, aggregating CLIP-based semantic and physical metrics, versus 53.2 for the strongest adapted baseline. Code: https://github.com/gmum/STAGE/ Project Page https://gmum.github.io/STAGE/

发表机构

• Jagiellonian University（雅盖隆大学）
• IDEAS Research Institute（IDEAS研究所）

机构由 AI 辅助整理，请以论文原文为准。