Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow

TL;DR

Easy3E introduces a fast, feed-forward 3D editing framework that achieves globally consistent and high-fidelity modifications from a single view, overcoming limitations of previous iterative methods.

Contribution

The paper presents a novel TRELLIS-based framework with Voxel FlowEdit and a normal-guided module for efficient, single-pass 3D editing with high fidelity and consistency.

Findings

Enables fast 3D editing from a single view.

Achieves globally consistent 3D deformations.

Restores high-frequency textures effectively.

Abstract

Existing 3D editing methods rely on computationally intensive scene-by-scene iterative optimization and suffer from multi-view inconsistency. We propose an effective and feed-forward 3D editing framework based on the TRELLIS generative backbone, capable of modifying 3D models from a single editing view. Our framework addresses two key issues: adapting training-free 2D editing to structured 3D representations, and overcoming the bottleneck of appearance fidelity in compressed 3D features. To ensure geometric consistency, we introduce Voxel FlowEdit, an edit-driven flow in the sparse voxel latent space that achieves globally consistent 3D deformation in a single pass. To restore high-fidelity details, we develop a normal-guided single to multi-view generation module as an external appearance prior, successfully recovering high-frequency textures. Experiments demonstrate that our method enables fast, globally consistent, and high-fidelity 3D model editing.