HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator

TL;DR

HEIE introduces a hierarchical, explainable framework leveraging multimodal large language models to evaluate and interpret the quality of AI-generated images, addressing issues of artifact detection and explainability.

Contribution

The paper presents HEIE, a novel hierarchical explainable evaluator that combines heatmaps, scores, and reasoning to improve defect localization and interpretability in AIGC images.

Findings

Achieves state-of-the-art performance in image implausibility evaluation

Provides detailed explanations for detected defects

Introduces a new dataset for interpretable AIGC image assessment

Abstract

AIGC images are prevalent across various fields, yet they frequently suffer from quality issues like artifacts and unnatural textures. Specialized models aim to predict defect region heatmaps but face two primary challenges: (1) lack of explainability, failing to provide reasons and analyses for subtle defects, and (2) inability to leverage common sense and logical reasoning, leading to poor generalization. Multimodal large language models (MLLMs) promise better comprehension and reasoning but face their own challenges: (1) difficulty in fine-grained defect localization due to the limitations in capturing tiny details, and (2) constraints in providing pixel-wise outputs necessary for precise heatmap generation. To address these challenges, we propose HEIE: a novel MLLM-Based Hierarchical Explainable Image Implausibility Evaluator. We introduce the CoT-Driven Explainable Trinity Evaluator, which integrates heatmaps, scores, and explanation outputs, using CoT to decompose complex tasks into subtasks of increasing difficulty and enhance interpretability. Our Adaptive Hierarchical Implausibility Mapper synergizes low-level image features with high-level mapper tokens from LLMs, enabling precise local-to-global hierarchical heatmap predictions through an uncertainty-based adaptive token approach. Moreover, we propose a new dataset: Expl-AIGI-Eval, designed to facilitate interpretable implausibility evaluation of AIGC images. Our method demonstrates state-of-the-art performance through extensive experiments. Our project is at https://yfthu.github.io/HEIE/.