EditP23: 3D Editing via Propagation of Image Prompts to Multi-View
This addresses the need for intuitive 3D editing without text prompts or explicit masks, though it appears incremental as it builds on pre-trained multi-view diffusion models.
The paper tackles the problem of mask-free 3D editing by propagating 2D image edits to multi-view representations in a 3D-consistent manner, achieving high fidelity to the source without manual masks.
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.