An Evolutionary Agentic Approach for Open-ended Image Quality Perception

2026-09-19

AI Summary

该研究针对现有图像质量评估模型难以扩展到开放感知维度的问题，提出了一种基于多代理协作进化的无需训练框架PACE，通过构建具体的视觉问答协议来改进图像质量评分。

Abstract

Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plausibility and text-rendering correctness. However, existing IQA models rely on fixed definitions and heavy supervision, making them difficult to extend to open-ended perceptual dimensions. We identify holistic bias as an important limitation: when scoring an unseen dimension, models reuse generic quality priors, leading to scoring errors and rank inversion. To address this, we propose PACE (Perceptual Agentic Collaborative Evolution), a training-free multi-agent framework that formulates open-ended IQA as explicit protocol construction. Given a target dimension, PACE uses collaborative agents to construct an evaluation protocol composed of verifiable Visual Question Answering (VQA) probes, grounding evaluation in concrete visual evidence rather than holistic impressions. The resulting protocol is calibrated using only four human-annotated images per dimension, while a dual-track scoring mechanism aligns model perception with human scoring scales. Across traditional IQA, structural fidelity, context-aware aesthetics, and newly defined open-ended dimensions, PACE consistently improves its MLLM backbone, achieving competitive performance across diverse IQA settings, and reduces the Holistic Override Rate (HOR) from 44.4\% to 8.6\%.

Problem

• Image Quality Assessment
• Open-ended Dimensions
• Holistic Bias
• Perceptual Evaluation

Innovation

• Evolutionary Agentic Approach
• Open-ended Image Quality Perception
• Visual Question Answering (VQA)
• Holistic Bias
• Dual-track Scoring Mechanism