CraftMesh：基于泊松无缝融合的高保真生成式网格操控
CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion
把三维网格编辑拆成「二维图像编辑 + 局部三维生成 + 泊松无缝融合」的流水线，其中混合 SDF/网格表示配合法向混合做几何融合、泊松纹理协调做外观融合，这两步可直接迁移到任何需要把新生成的三维局部拼回已有网格的任务（如三维补全、局部重生成、资产编辑）。
原文依据 Poisson Geometric Fusion, which utilizes a hybrid SDF/Mesh representation with normal blending to achieve harmonious geometric integration
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论可控、高保真的网格编辑在三维内容创作领域仍是一项重大挑战。现有生成式方法往往难以处理复杂几何，且无法保留细粒度细节。我们提出 CraftMesh，一个基于泊松无缝融合的高保真生成式网格操控新框架。我们将网格编辑分解为一条充分利用二维图像编辑与三维生成模型各自优势的流水线：首先编辑二维参考图像，然后生成与编辑区域对应的三维网格，并通过几何与纹理融合方法将其无缝融合进原始网格。我们引入两项核心技术：泊松几何融合，利用带法向混合的混合 SDF/网格表示实现和谐的几何整合；以及泊松纹理协调，实现视觉一致的纹理混合。我们在具有挑战性的编辑场景中展示了最优的结构一致性、几何保真度与纹理质量。
英文原文摘要 1024 字符
Controllable, high-fidelity mesh editing remains a significant challenge in the domain of 3D content creation. Existing generative methods often struggle with complex geometries and fail to preserve fine-scale details. We propose CraftMesh, a novel framework for high-fidelity generative mesh manipulation based on Poisson Seamless Fusion. We decompose mesh editing into a pipeline that leverages the strengths of 2D image editing and 3D generation models: we first edit a 2D reference image, then generate a 3D mesh corresponding to the edited region, and fuse it seamlessly into the original mesh through a Geometry and Texture Fusion method. We introduce two core techniques: Poisson Geometric Fusion, which utilizes a hybrid SDF/Mesh representation with normal blending to achieve harmonious geometric integration, and Poisson Texture Harmonization for visually consistent texture blending. We demonstrate state-of-the-art structural consistency, geometric fidelity, and texture quality in challenging editing scenarios.