无需训练即可精准编辑3D生成模型，避免结构失真。
TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization
- 在生成动态切空间中逐令牌控制，实现细粒度编辑
- 相比基线减少结构瑕疵，性能达当前最优
- 适合需要快速、无训练编辑3D内容的开发者
近期基于流匹配的3D生成模型（如VecSet）采用结构化表示，其令牌共享全局上下文，导致传统无训练编辑出现语义伪影，如保留区域坍缩或变换不完整。为此，我们提出TanGO，一种无需训练的框架，通过生成动力学的切空间实现自适应的逐令牌引导与优化。为实现选择性控制，我们建立一步最优控制规则，并利用源与目标速度场间的冯·米塞斯-费舍尔启发式方向差异，确定每个令牌控制信号的强度。实验表明，TanGO显著降低结构伪影，性能优于现有3D编辑基线。代码已公开于https://github.com/siw00-lim/TanGO。
原文摘要 · Abstract (English)
While recent flow-matching 3D generative models (e.g., VecSet) adopt structured representations, their tokens share global context, causing conventional training-free editing to suffer from semantic artifacts such as collapsed preserved regions or incomplete transformations. To address this, we propose TanGO, a training-free framework that enables adaptive per-token steering in the tangent space of generative dynamics. To realize this selective control, we formulate a one-step optimal control rule and determine the strength of each token's control signal using a von Mises-Fisher inspired directional discrepancy derived from the source and target velocity fields. Experiments show that TanGO substantially reduces structural artifacts and achieves state-of-the-art performance, outperforming existing 3D editing baselines. The code is publicly available at https://github.com/siw00-lim/TanGO.
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。