CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions

TL;DR

CREval introduces an automated, interpretable evaluation framework and benchmark for assessing creative image manipulation models under complex instructions, addressing gaps in existing evaluation methods.

Contribution

It presents CREval, a QA-based evaluation pipeline, and CREval-Bench, a comprehensive benchmark for complex, creative image editing tasks, with extensive evaluation results.

Findings

Closed-source models outperform open-source ones on complex tasks.

All models still face significant challenges in effective creative editing.

CREval's metrics strongly align with human judgments.

Abstract

Instruction-based multimodal image manipulation has recently made rapid progress. However, existing evaluation methods lack a systematic and human-aligned framework for assessing model performance on complex and creative editing tasks. To address this gap, we propose CREval, a fully automated question-answer (QA)-based evaluation pipeline that overcomes the incompleteness and poor interpretability of opaque Multimodal Large Language Models (MLLMs) scoring. Simultaneously, we introduce CREval-Bench, a comprehensive benchmark specifically designed for creative image manipulation under complex instructions. CREval-Bench covers three categories and nine creative dimensions, comprising over 800 editing samples and 13K evaluation queries. Leveraging this pipeline and benchmark, we systematically evaluate a diverse set of state-of-the-art open and closed-source models. The results reveal that while closed-source models generally outperform open-source ones on complex and creative tasks, all models still struggle to complete such edits effectively. In addition, user studies demonstrate strong consistency between CREval's automated metrics and human judgments. Therefore, CREval provides a reliable foundation for evaluating image editing models on complex and creative image manipulation tasks, and highlights key challenges and opportunities for future research.