LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning

TL;DR

LayerEdit is a novel, training-free multi-object image editing framework that achieves conflict-free, disentangled modifications of multiple objects guided by text, by decomposing, editing, and fusing object layers with conflict awareness.

Contribution

This work introduces LayerEdit, a new multi-layer disentangled editing framework that effectively handles inter-object conflicts without training, enabling precise multi-object editing guided by text.

Findings

Outperforms existing methods in intra-object controllability.

Achieves high inter-object coherence in complex scenarios.

Demonstrates effective conflict suppression during editing.

Abstract

Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localize-editing paradigm, focusing on independent object localization and editing while neglecting critical inter-object interactions. However, this work points out that the neglected attention entanglements in inter-object conflict regions, inherently hinder disentangled multi-object editing, leading to either inter-object editing leakage or intra-object editing constraints. We thereby propose a novel multi-layer disentangled editing framework LayerEdit, a training-free method which, for the first time, through precise object-layered decomposition and coherent fusion, enables conflict-free object-layered editing. Specifically, LayerEdit introduces a novel "decompose-editingfusion" framework, consisting of: (1) Conflict-aware Layer Decomposition module, which utilizes an attention-aware IoU scheme and time-dependent region removing, to enhance conflict awareness and suppression for layer decomposition. (2) Object-layered Editing module, to establish coordinated intra-layer text guidance and cross-layer geometric mapping, achieving disentangled semantic and structural modifications. (3) Transparency-guided Layer Fusion module, to facilitate structure-coherent inter-object layer fusion through precise transparency guidance learning. Extensive experiments verify the superiority of LayerEdit over existing methods, showing unprecedented intra-object controllability and inter-object coherence in complex multi-object scenarios. Codes are available at: https://github.com/fufy1024/LayerEdit.