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

Yuhan Pu; Hao Zheng; Ziqian Mo; Zirui Pang; Hill Zhang; Tianyi Fan; Shuhong Wu; Jiaheng Wei

cs.CVApr 3, 2026

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

Authors: Yuhan Pu, Hao Zheng, Ziqian Mo, Zirui Pang, Hill Zhang, Tianyi Fan, Shuhong Wu, Jiaheng Wei

Organizations: The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China · Harbin Institute of Technology, Weihai, Shandong, China · Shenzhen University, Shenzhen, Guangdong, China · Claremont McKenna College, Claremont, California, USA ·

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 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.

Figures & tables

Figure 1: Compare CAMEO with other State-of-the-Art image editing models

Panel of Figure 2 — Figure 2: Representative failure cases illustrating common issues of conditional image editing on images from BDD100K under complex situations.

Figure 3: Overview of the CAMEO multi-agent workflow. The Strategic Director coordinates multiple agents to perform task interpretation, structured generation, quality evaluation, and iterative refinement.

Panel of Figure 4 — Figure 4: Representative cases of how CAMEO improves semantic correctness and physical plausibility issues.

Panel of Figure 5 — Figure 5: Representative cases of how CAMEO improves boundary blending and contextual coherence issues.

Panel of Table 1 — Table 1: Pairwise win/lose/tie statistics (%) on the road anomaly insertion task across multiple vision-language judges. Higher win rates indicate stronger performance of CAMEO over direct editing.

Panel of Table 2 — Table 2: Pairwise win/lose/tie statistics (%) on the human pose switching task across multiple vision-language judges. Higher win rates indicate stronger performance of CAMEO over direct editing.

Panel of Table 3 — Table 3: Average evaluation scores (1-10 scale) of CAMEO and direct editing baselines under four vision-language judges on the road anomaly insertion task. CAMEO consistently achieves higher scores across all judges.

Panel of Table 4 — Table 4: Average evaluation scores (1-10 scale) of CAMEO and direct editing baselines under four vision-language judges on the human pose switching task. CAMEO consistently achieves higher scores across most judges.

Figure 6: Qualitative comparison across methods on diverse human pose switching examples. Each input consists of an instruction and an original image. Instructions are: Row 1: a high front kick with the right leg extended forward, upper body leaning back for balance. Row 2: a running posture with the right leg stepping forward, left leg pushing back. Row 3: a side stretching pose bending the torso to the right with left arm reaching overhead. Row 4: a high front kick with the right leg extended forward, upper body leaning back for balance.

Baseline	Win	Lose	Tie	Net $\uparrow$
Qwen-Image-Edit-Plus	56.4	22.1	21.5	+34.3
Nano Banana Pro	39.8	28.6	31.6	+11.2
Flux-2-Pro	47.5	24.3	28.2	+23.2
Seedream-4.5	33.7	29.4	36.9	+4.3

Table 5: Human evaluation results (%) comparing CAMEO with direct editing baselines.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 7: Qualitative comparison of the full CAMEO system and three ablation variants. Removing key components leads to degraded realism and quality of details.

Ablation Setting	Qwen3-VL-Plus	GPT-4o	Gemini-2.5	Claude-Opus-4.5
Full Model (CAMEO)	8.47	8.42	8.36	8.45
w/o Adaptive Reference Grounding	7.88	7.91	7.80	7.83
w/o Quality Control	7.05	7.18	7.10	6.96
w/o Iterative Refinement	7.96	7.99	7.92	7.94

Appendix

Table 6: Ablation study of CAMEO on the road anomaly insertion task. Average evaluation scores (1–10 scale) reported by four vision-language judges.

Ablation Setting	Qwen3-VL-Plus	GPT-4o	Gemini-2.5	Claude-Opus-4.5
Full Model (CAMEO)	8.39	8.33	8.27	8.35
w/o Adaptive Reference Grounding	7.83	7.86	7.74	7.79
w/o Quality Control	6.98	7.12	7.05	6.91
w/o Iterative Refinement	7.91	7.88	7.82	7.86

Appendix

Table 7: Ablation study of CAMEO on the human pose switching task. Average evaluation scores (1–10 scale) reported by four vision-language judges.

Figure 8: Screenshot of the human evaluation interface used in our study.

Image Editing

Image editing changes selected visual content while preserving the parts of an image that should remain unchanged.

See all 315 papers

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning
Mar 9, 2026Yiran Zhao, Yaoqi Ye, Xiang Liu +2Image Editing RL for Image Editing
National University of Singapore · Adobe Research
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
Oct 15, 2026Sara Dorfman, Nir Goren, Gal Barak +2Multi-Turn Image Editing Image Editing
Tel Aviv University
GMO-E $^2$ DIT: Grounded Multi-Operation Editing for E-Commerce Images
Jul 1, 2026Zipeng Guo, Xiaoan Liu, Lichen Ma +9Image Editing Evaluation Text-Guided Image Editing
Wuhan University · Xi’an Jiaotong University · Sun Yat-sen University

Mar 9, 2026J/K move · Enter open · S save

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning

Yiran Zhao, Yaoqi Ye, Xiang Liu, Michael Qizhe Shieh+1

National University of Singapore · Adobe Research

Image Editing RL for Image Editing Multimodal Agents Sequential MARL

Open paper AskPDF arXiv

With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly closed-source or proprietary models, often struggle with complex, indirect, or multi-step user instructions. These limitations hinder their ability to perform nuanced, context-aware edits that align with human intent. In this work, we propose ImageEdit-R1, a multi-agent framework for intelligent image editing that leverages reinforcement learning to coordinate high-level decision-making across a set of specialized, pretrained vision-language and generative agents. Each agent is responsible for distinct capabilities--such as understanding user intent, identifying regions of interest, selecting appropriate editing actions, and synthesizing visual content--while reinforcement learning governs their collaboration to ensure coherent and goal-directed behavior. Unlike existing approaches that rely on monolithic models or hand-crafted pipelines, our method treats image editing as a sequential decision-making problem, enabling dynamic and context-aware editing strategies. Experimental results demonstrate that ImageEdit-R1 consistently outperforms both individual closed-source diffusion models and alternative multi-agent framework baselines across multiple image editing datasets.

Abstract

Image Editing

Explore similar work

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning

ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning

GMO-E2^22DIT: Grounded Multi-Operation Editing for E-Commerce Images

GMO-E $^2$ DIT: Grounded Multi-Operation Editing for E-Commerce Images