Search papers, labs, and topics across Lattice.
EditP23 introduces a novel approach to 3D editing by propagating 2D image edits to multi-view representations without requiring masks or text prompts. The method leverages a pair of original and edited images to guide an edit-aware flow within the latent space of a pre-trained multi-view diffusion model. This allows for consistent propagation of edits across different views while preserving object identity and requiring no optimization.
Forget tedious masks and prompts: EditP23 lets you edit 3D objects just by showing the model a before-and-after image pair.
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.
