无需训练即可稳定编辑3D模型，保持形状完整且语义准确。
AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows
- 通过全局共享的潜在锚点保证编辑过程一致性。
- 在Eval3DEdit上实现多种编辑类型下的稳定结构与语义对齐。
- 无需掩码监督，适合快速、高质量的3D内容创作。
免训练3D编辑旨在不微调模型的情况下，根据人类指令修改3D形状，对3D内容生成至关重要。然而，现有方法常因扩散采样中随时间步变化的噪声导致潜在锚点不一致，难以生成强效且几何稳定的编辑结果。为此，我们提出AnchorFlow，基于潜在锚点一致性原则设计：建立源与目标轨迹间的全局共享潜在锚点，结合松弛的锚点对齐损失与锚点对齐更新规则，确保变换全程稳定且语义忠实。该设计稳定了潜在参考空间，支持更显著的语义修改。此外，AnchorFlow无需掩码监督，能有效保持几何保真度。在Eval3DEdit基准上的实验表明，AnchorFlow在多种编辑类型下均能持续生成语义对齐且结构稳健的编辑结果。代码已公开于https://github.com/ZhenglinZhou/AnchorFlow。
原文摘要 · Abstract (English)
Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geometrically stable edits, largely due to inconsistent latent anchors introduced by timestep-dependent noise during diffusion sampling. To address these limitations, we introduce AnchorFlow, which is built upon the principle of latent anchor consistency. Specifically, AnchorFlow establishes a global latent anchor shared between the source and target trajectories, and enforces coherence using a relaxed anchor-alignment loss together with an anchor-aligned update rule. This design ensures that transformations remain stable and semantically faithful throughout the editing process. By stabilizing the latent reference space, AnchorFlow enables more pronounced semantic modifications. Moreover, AnchorFlow is mask-free. Without mask supervision, it effectively preserves geometric fidelity. Experiments on the Eval3DEdit benchmark show that AnchorFlow consistently delivers semantically aligned and structurally robust edits across diverse editing types. Code is at https://github.com/ZhenglinZhou/AnchorFlow.
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。