Make Your MoVe: Make Your 3D Contents by Adapting Multi-View Diffusion Models to External Editing

TL;DR

This paper introduces a tuning-free, plug-and-play method for editing 3D content that preserves geometry and enhances multi-view consistency, addressing limitations of existing 2D-focused editing tools.

Contribution

It proposes a novel geometry preservation module and injection switcher to improve 3D editing quality without additional training.

Findings

Improves multi-view consistency of edited 3D assets

Enhances mesh quality after editing

Works across various diffusion models and editing methods

Abstract

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.