CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editing

TL;DR

CoreEditor introduces a correspondence-constrained diffusion framework for consistent and high-quality text-driven 3D editing, effectively maintaining multi-view consistency and enabling user-controlled editing results.

Contribution

It proposes a novel correspondence-constrained attention mechanism and a semantic similarity integration for improved multi-view 3D editing consistency.

Findings

Produces sharper, more consistent 3D edits

Outperforms prior methods in quality and consistency

Offers flexible user-controlled editing options

Abstract

Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view inputs. However, without explicit control over multi-view information exchange, they often fail to maintain cross-view consistency, leading to insufficient edits and blurry details. We introduce CoreEditor, a novel framework for consistent text-to-3D editing. The key innovation is a correspondence-constrained attention mechanism that enforces precise interactions between pixels expected to remain consistent throughout the diffusion denoising process. Beyond relying solely on geometric alignment, we further incorporate semantic similarity estimated during denoising, enabling more reliable correspondence modeling and robust multi-view editing. In addition, we design a selective editing pipeline that allows users to choose preferred results from multiple candidates, offering greater flexibility and user control. Extensive experiments show that CoreEditor produces high-quality, 3D-consistent edits with sharper details, significantly outperforming prior methods.