CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator

TL;DR

CAMEO introduces a multi-agent, feedback-driven framework for conditional image editing that enhances quality, robustness, and structural accuracy over traditional single-step methods.

Contribution

It reformulates image editing as an iterative, quality-aware process with structured feedback, improving control and consistency in complex editing tasks.

Findings

CAMEO achieves 20% higher win rate on average compared to state-of-the-art models.

The framework improves robustness and structural reliability in image editing.

Evaluation embedded within the editing loop enables iterative refinement and quality control.

Abstract

Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose \textbf{CAMEO}, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.