Make Your MoVe: Make Your 3D Contents by Adapting Multi-View Diffusion Models to External Editing
This addresses the need for personalized 3D content editing, offering a practical solution for users in 3D generation and design, though it is incremental as it builds on existing multi-view diffusion models.
The paper tackles the problem of editing 3D content by adapting multi-view diffusion models to external editing methods, proposing a tuning-free scheme that improves multi-view consistency and mesh quality without compromising geometry.
As 3D generation techniques continue to flourish, the demand for generating personalized content is rapidly rising. Users increasingly seek to apply various editing methods to polish generated 3D content, aiming to enhance its color, style, and lighting without compromising the underlying geometry. However, most existing editing tools focus on the 2D domain, and directly feeding their results into 3D generation methods (like multi-view diffusion models) will introduce information loss, degrading the quality of the final 3D assets. In this paper, we propose a tuning-free, plug-and-play scheme that aligns edited assets with their original geometry in a single inference run. Central to our approach is a geometry preservation module that guides the edited multi-view generation with original input normal latents. Besides, an injection switcher is proposed to deliberately control the supervision extent of the original normals, ensuring the alignment between the edited color and normal views. Extensive experiments show that our method consistently improves both the multi-view consistency and mesh quality of edited 3D assets, across multiple combinations of multi-view diffusion models and editing methods.