Abstract
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. Our key insight is to decompose mesh editing into a pipeline that leverages the strengths of 2D image editing and 3D generative modeling: 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 Joint Geometry and Appearance Fusion framework built on a hybrid SDF/Mesh representation to enable Poisson Geometry Blending and Poisson Texture Harmonization. Experimental results demonstrate that CraftMesh outperforms state-of-the-art methods, delivering improved structural consistency, richer local geometric and appearance details in challenging editing scenarios.
Framework
Our framework follows an image editing–mesh generation–seamless fusion pipeline that fully leverages the strengths of 2D models for image editing and 3D models for high-quality mesh generation. First, Edited Region Mesh Generation produces meshes for the editing region. Then, a Joint Poisson and Appearence Fusion is applied to fuse the Edited Region Mesh with the Original Mesh.
Qualitative Comparisons
Qualitative comparisons show that our method produces harmonious geometry structure, intricate local details, and high-fidelity colors
BibTeX
@article{Hu2025Craftmesh,
title={CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion},
author={Jincheng, James and Wu, Yuxiao and Cai, Youcheng and Liu, Ligang},
journal={arXiv preprint arXiv:2509.13688},
year={2025}
}