EditP23: 3D Editing via Propagation of Image Prompts to Multi-View

TL;DR

EditP23 introduces a novel mask-free 3D editing technique that propagates 2D image edits across multiple views using a diffusion model, enabling intuitive, identity-preserving 3D modifications without manual masks or optimization.

Contribution

It is the first method to enable multi-view consistent 3D editing guided solely by image prompts without masks or optimization, leveraging a diffusion model for coherent propagation.

Findings

High fidelity in 3D object editing across various categories

No manual masks or optimization required

Effective propagation of edits across views

Abstract

We present EditP23, a method for mask-free 3D editing that propagates 2D image edits to multi-view representations in a 3D-consistent manner. In contrast to traditional approaches that rely on text-based prompting or explicit spatial masks, EditP23 enables intuitive edits by conditioning on a pair of images: an original view and its user-edited counterpart. These image prompts are used to guide an edit-aware flow in the latent space of a pre-trained multi-view diffusion model, allowing the edit to be coherently propagated across views. Our method operates in a feed-forward manner, without optimization, and preserves the identity of the original object, in both structure and appearance. We demonstrate its effectiveness across a range of object categories and editing scenarios, achieving high fidelity to the source while requiring no manual masks.