Easy3E：基于矫正体素流的前馈三维资产编辑
Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow
将免训练的 2D 编辑适配到稀疏体素潜空间，通过单次前馈的体素流实现全局一致的 3D 变形，并用法线引导的单视图到多视图生成恢复高频纹理，为 3D 资产编辑提供了可复用的高效范式。
原文依据 we introduce Voxel FlowEdit, an edit-driven flow in the sparse voxel latent space that achieves globally consistent 3D deformation in a single pass.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的三维编辑方法依赖于计算密集的逐场景迭代优化，并且存在多视图不一致的问题。我们提出了一种有效的前馈三维编辑框架，基于 TRELLIS 生成骨干网络，能够从单个编辑视图修改三维模型。我们的框架解决了两个关键问题：将免训练的二维编辑适配到结构化三维表示，以及克服压缩三维特征中外观保真度的瓶颈。为确保几何一致性，我们引入了 Voxel FlowEdit，一种在稀疏体素潜空间中的编辑驱动流，能够在单次前向传播中实现全局一致的三维变形。为恢复高保真细节，我们开发了一个法线引导的单视图到多视图生成模块作为外部外观先验，成功恢复了高频纹理。实验表明，我们的方法能够实现快速、全局一致且高保真的三维模型编辑。
英文原文摘要 967 字符
Existing 3D editing methods rely on computationally intensive scene-by-scene iterative optimization and suffer from multi-view inconsistency. We propose an effective and feed-forward 3D editing framework based on the TRELLIS generative backbone, capable of modifying 3D models from a single editing view. Our framework addresses two key issues: adapting training-free 2D editing to structured 3D representations, and overcoming the bottleneck of appearance fidelity in compressed 3D features. To ensure geometric consistency, we introduce Voxel FlowEdit, an edit-driven flow in the sparse voxel latent space that achieves globally consistent 3D deformation in a single pass. To restore high-fidelity details, we develop a normal-guided single to multi-view generation module as an external appearance prior, successfully recovering high-frequency textures. Experiments demonstrate that our method enables fast, globally consistent, and high-fidelity 3D model editing.