Zero-shot Image Editing with Reference Imitation

TL;DR

This paper introduces MimicBrush, a diffusion-based generative framework enabling zero-shot image editing by imitating reference images without requiring direct correspondence, thus enhancing user creativity and flexibility.

Contribution

The work presents a novel imitative editing paradigm and a self-supervised training method that captures semantic correspondence from in-the-wild references for flexible image editing.

Findings

Outperforms existing image editing methods in various scenarios

Effectively captures semantic relations between images without supervision

Establishes a new benchmark for reference-based image editing

Abstract

Image editing serves as a practical yet challenging task considering the diverse demands from users, where one of the hardest parts is to precisely describe how the edited image should look like. In this work, we present a new form of editing, termed imitative editing, to help users exercise their creativity more conveniently. Concretely, to edit an image region of interest, users are free to directly draw inspiration from some in-the-wild references (e.g., some relative pictures come across online), without having to cope with the fit between the reference and the source. Such a design requires the system to automatically figure out what to expect from the reference to perform the editing. For this purpose, we propose a generative training framework, dubbed MimicBrush, which randomly selects two frames from a video clip, masks some regions of one frame, and learns to recover the masked regions using the information from the other frame. That way, our model, developed from a diffusion prior, is able to capture the semantic correspondence between separate images in a self-supervised manner. We experimentally show the effectiveness of our method under various test cases as well as its superiority over existing alternatives. We also construct a benchmark to facilitate further research.