MCIE: Multimodal LLM-Driven Complex Instruction Image Editing with Spatial Guidance

TL;DR

This paper introduces MCIE-E1, a multimodal large language model-driven approach for complex instruction image editing that improves instruction compliance and background consistency using spatial and background modules, supported by a new dataset and benchmark.

Contribution

The paper presents a novel architecture with spatial-aware and background-consistent modules, a dedicated data pipeline, and a new benchmark for complex instruction image editing.

Findings

Achieves 23.96% improvement in instruction compliance.

Outperforms previous methods in quantitative and qualitative evaluations.

Introduces CIE-Bench with new evaluation metrics.

Abstract

Recent advances in instruction-based image editing have shown remarkable progress. However, existing methods remain limited to relatively simple editing operations, hindering real-world applications that require complex and compositional instructions. In this work, we address these limitations from the perspectives of architectural design, data, and evaluation protocols. Specifically, we identify two key challenges in current models: insufficient instruction compliance and background inconsistency. To this end, we propose MCIE-E1, a Multimodal Large Language Model-Driven Complex Instruction Image Editing method that integrates two key modules: a spatial-aware cross-attention module and a background-consistent cross-attention module. The former enhances instruction-following capability by explicitly aligning semantic instructions with spatial regions through spatial guidance during the denoising process, while the latter preserves features in unedited regions to maintain background consistency. To enable effective training, we construct a dedicated data pipeline to mitigate the scarcity of complex instruction-based image editing datasets, combining fine-grained automatic filtering via a powerful MLLM with rigorous human validation. Finally, to comprehensively evaluate complex instruction-based image editing, we introduce CIE-Bench, a new benchmark with two new evaluation metrics. Experimental results on CIE-Bench demonstrate that MCIE-E1 consistently outperforms previous state-of-the-art methods in both quantitative and qualitative assessments, achieving a 23.96% improvement in instruction compliance.