3D-LATTE：基于文本指令的潜空间三维编辑
3D-LATTE: Latent Space 3D Editing from Textual Instructions
把指令编辑从 2D 先验蒸馏搬到原生 3D 扩散模型的潜空间里做，用源物体的 3D 注意力图混合来定位编辑区域，并用傅里叶域谱调制加几何感知正则化抑制多视角不一致——这套「潜空间注意力引导 + 频域正则」的组合可直接迁移到 3D 生成模型的可控编辑与局部重绘。
原文依据 we propose a novel editing method that operates within the latent space of a native 3D diffusion model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管多视角扩散模型在基于文本/图像的 3D 资产生成上近期取得了成功，但基于指令的 3D 资产编辑在质量上却令人意外地远远落后于生成模型。主要原因是近期采用 2D 先验的方法受困于视角不一致的编辑信号。我们超越了 2D 先验蒸馏方法与多视角编辑策略，提出一种在原生 3D 扩散模型的潜空间内运行的新颖编辑方法，使我们能够直接操控 3D 几何。我们通过将生成过程中的 3D 注意力图与源物体进行混合来引导编辑合成。结合几何感知正则化引导、傅里叶域中的谱调制策略以及用于 3D 增强的精修步骤，我们的方法优于先前的 3D 编辑方法，能够在广泛的形状与语义操控上实现高保真且精确的编辑。项目网页为 https://mparelli.github.io/3d-latte。
英文原文摘要 997 字符
Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality of generation models. The main reason is that recent approaches using 2D priors suffer from view-inconsistent editing signals. Going beyond 2D prior distillation methods and multi-view editing strategies, we propose a novel editing method that operates within the latent space of a native 3D diffusion model, allowing us to directly manipulate 3D geometry. We guide the edit synthesis by blending 3D attention maps from the generation with the source object. Coupled with geometry-aware regularization guidance, a spectral modulation strategy in the Fourier domain and a refinement step for 3D enhancement, our method outperforms previous 3D editing methods enabling high-fidelity and precise edits across a wide range of shapes and semantic manipulations. Our project webpage is https://mparelli.github.io/3d-latte.