FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing

TL;DR

FlexEdit is a novel framework for object-centric image editing that iteratively adjusts latents during denoising, enabling realistic, controllable, and seamless object modifications with automatic background protection.

Contribution

We introduce FlexEdit, a flexible, controllable object editing framework that optimizes latents iteratively and employs adaptive masks for seamless object editing.

Findings

Outperforms recent text-guided image editing methods.

Demonstrates versatility across various editing scenarios.

Introduces new evaluation metrics for object-centric editing.

Abstract

Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce FlexEdit, a flexible and controllable editing framework for objects where we iteratively adjust latents at each denoising step using our FlexEdit block. Initially, we optimize latents at test time to align with specified object constraints. Then, our framework employs an adaptive mask, automatically extracted during denoising, to protect the background while seamlessly blending new content into the target image. We demonstrate the versatility of FlexEdit in various object editing tasks and curate an evaluation test suite with samples from both real and synthetic images, along with novel evaluation metrics designed for object-centric editing. We conduct extensive experiments on different editing scenarios, demonstrating the superiority of our editing framework over recent advanced text-guided image editing methods. Our project page is published at https://flex-edit.github.io/.